Search

LLM-as-a-Judge is a novel solution that can assess textual information with large language models (LLMs). Based on existing research studies, LLMs demonstrate remarkable performance in providing a compelling alternative to traditional human assessment. However, the robustness of these systems against prompt injection attacks remains an open question. In this work, we introduce JudgeDeceiver, a novel optimization-based prompt injection attack tailored to LLM-as-a-Judge. Our method formulates a precise optimization objective for attacking the decision-making process of LLM-as-a-Judge and utilizes an optimization algorithm to efficiently automate the generation of adversarial sequences, achieving targeted and effective manipulation of model evaluations. Compared to handcraft prompt injection attacks, our method demonstrates superior efficacy, posing a significant challenge to the current security paradigms of LLM-based judgment systems. Through extensive experiments, we showcase the capability of JudgeDeceiver in altering decision outcomes across various cases, highlighting the vulnerability of LLM-as-a-Judge systems to the optimization-based prompt injection attack.

Recent studies have revealed that federated learning (FL), once considered secure due to clients not sharing their private data with the server, is vulnerable to attacks such as client-side training data distribution inference, where a malicious client can recreate the victim's data. While various countermeasures exist, they are not practical, often assuming server access to some training data or knowledge of label distribution before the attack. In this work, we bridge the gap by proposing InferGuard, a novel Byzantine-robust aggregation rule aimed at defending against client-side training data distribution inference attacks. In our proposed InferGuard, the server first calculates the coordinate-wise median of all the model updates it receives. A client's model update is considered malicious if it significantly deviates from the computed median update. We conduct a thorough evaluation of our proposed InferGuard on five benchmark datasets and perform a comparison with ten baseline methods. The results of our experiments indicate that our defense mechanism is highly effective in protecting against client-side training data distribution inference attacks, even against strong adaptive attacks. Furthermore, our method substantially outperforms the baseline methods in various practical FL scenarios., Comment: To appear in The Web Conference 2024 (WWW '24)

Foundation model has become the backbone of the AI ecosystem. In particular, a foundation model can be used as a general-purpose feature extractor to build various downstream classifiers. However, foundation models are vulnerable to backdoor attacks and a backdoored foundation model is a single-point-of-failure of the AI ecosystem, e.g., multiple downstream classifiers inherit the backdoor vulnerabilities simultaneously. In this work, we propose Mudjacking, the first method to patch foundation models to remove backdoors. Specifically, given a misclassified trigger-embedded input detected after a backdoored foundation model is deployed, Mudjacking adjusts the parameters of the foundation model to remove the backdoor. We formulate patching a foundation model as an optimization problem and propose a gradient descent based method to solve it. We evaluate Mudjacking on both vision and language foundation models, eleven benchmark datasets, five existing backdoor attacks, and thirteen adaptive backdoor attacks. Our results show that Mudjacking can remove backdoor from a foundation model while maintaining its utility., Comment: To appear in USENIX Security Symposium, 2024

Visual hallucination (VH) means that a multi-modal LLM (MLLM) imagines incorrect details about an image in visual question answering. Existing studies find VH instances only in existing image datasets, which results in biased understanding of MLLMs' performance under VH due to limited diversity of such VH instances. In this work, we propose a tool called VHTest to generate a diverse set of VH instances. Specifically, VHTest finds some initial VH instances in existing image datasets (e.g., COCO), generates a text description for each VH mode, and uses a text-to-image generative model (e.g., DALL-E-3) to generate VH images based on the text descriptions. We collect a benchmark dataset with 1,200 VH instances in 8 VH modes using VHTest. We find that existing MLLMs such as GPT-4V, LLaVA-1.5, and MiniGPT-v2 hallucinate for a large fraction of the instances in our benchmark. Moreover, we find that fine-tuning an MLLM using our benchmark dataset reduces its likelihood to hallucinate without sacrificing its performance on other benchmarks. Our benchmarks are publicly available: https://github.com/wenhuang2000/VHTest.

Federated recommendation is a prominent use case within federated learning, yet it remains susceptible to various attacks, from user to server-side vulnerabilities. Poisoning attacks are particularly notable among user-side attacks, as participants upload malicious model updates to deceive the global model, often intending to promote or demote specific targeted items. This study investigates strategies for executing promotion attacks in federated recommender systems. Current poisoning attacks on federated recommender systems often rely on additional information, such as the local training data of genuine users or item popularity. However, such information is challenging for the potential attacker to obtain. Thus, there is a need to develop an attack that requires no extra information apart from item embeddings obtained from the server. In this paper, we introduce a novel fake user based poisoning attack named PoisonFRS to promote the attacker-chosen targeted item in federated recommender systems without requiring knowledge about user-item rating data, user attributes, or the aggregation rule used by the server. Extensive experiments on multiple real-world datasets demonstrate that PoisonFRS can effectively promote the attacker-chosen targeted item to a large portion of genuine users and outperform current benchmarks that rely on additional information about the system. We further observe that the model updates from both genuine and fake users are indistinguishable within the latent space., Comment: To appear in The Web Conference 2024 (WWW '24)

Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness., Comment: This work is still under work and we welcome your contribution

Federated learning (FL) enables collaborative model training among multiple clients without raw data exposure. However, recent studies have shown that clients' private training data can be reconstructed from the gradients they share in FL, known as gradient inversion attacks (GIAs). While GIAs have demonstrated effectiveness under \emph{ideal settings and auxiliary assumptions}, their actual efficacy against \emph{practical FL systems} remains under-explored. To address this gap, we conduct a comprehensive study on GIAs in this work. We start with a survey of GIAs that establishes a milestone to trace their evolution and develops a systematization to uncover their inherent threats. Specifically, we categorize the auxiliary assumptions used by existing GIAs based on their practical accessibility to potential adversaries. To facilitate deeper analysis, we highlight the challenges that GIAs face in practical FL systems from three perspectives: \textit{local training}, \textit{model}, and \textit{post-processing}. We then perform extensive theoretical and empirical evaluations of state-of-the-art GIAs across diverse settings, utilizing eight datasets and thirteen models. Our findings indicate that GIAs have inherent limitations when reconstructing data under practical local training settings. Furthermore, their efficacy is sensitive to the trained model, and even simple post-processing measures applied to gradients can be effective defenses. Overall, our work provides crucial insights into the limited effectiveness of GIAs in practical FL systems. By rectifying prior misconceptions, we hope to inspire more accurate and realistic investigations on this topic.

Several companies--such as Google, Microsoft, and OpenAI--have deployed techniques to watermark AI-generated content to enable proactive detection. However, existing literature mainly focuses on user-agnostic detection. Attribution aims to further trace back the user of a generative-AI service who generated a given content detected as AI-generated. Despite its growing importance, attribution is largely unexplored. In this work, we aim to bridge this gap by providing the first systematic study on watermark-based, user-aware detection and attribution of AI-generated content. Specifically, we theoretically study the detection and attribution performance via rigorous probabilistic analysis. Moreover, we develop an efficient algorithm to select watermarks for the users to enhance attribution performance. Both our theoretical and empirical results show that watermark-based detection and attribution inherit the accuracy and (non-)robustness properties of the watermarking method.

A graph neural network (GNN) is a type of neural network that is specifically designed to process graph-structured data. Typically, GNNs can be implemented in two settings, including the transductive setting and the inductive setting. In the transductive setting, the trained model can only predict the labels of nodes that were observed at the training time. In the inductive setting, the trained model can be generalized to new nodes/graphs. Due to its flexibility, the inductive setting is the most popular GNN setting at the moment. Previous work has shown that transductive GNNs are vulnerable to a series of privacy attacks. However, a comprehensive privacy analysis of inductive GNN models is still missing. This paper fills the gap by conducting a systematic privacy analysis of inductive GNNs through the lens of link stealing attacks, one of the most popular attacks that are specifically designed for GNNs. We propose two types of link stealing attacks, i.e., posterior-only attacks and combined attacks. We define threat models of the posterior-only attacks with respect to node topology and the combined attacks by considering combinations of posteriors, node attributes, and graph features. Extensive evaluation on six real-world datasets demonstrates that inductive GNNs leak rich information that enables link stealing attacks with advantageous properties. Even attacks with no knowledge about graph structures can be effective. We also show that our attacks are robust to different node similarities and different graph features. As a counterpart, we investigate two possible defenses and discover they are ineffective against our attacks, which calls for more effective defenses., Comment: To appear in the 24th Privacy Enhancing Technologies Symposium (PETS 2024), July 15-20, 2024

Model poisoning attacks are critical security threats to Federated Learning (FL). Existing model poisoning attacks suffer from two key limitations: 1) they achieve suboptimal effectiveness when defenses are deployed, and/or 2) they require knowledge of the model updates or local training data on genuine clients. In this work, we make a key observation that their suboptimal effectiveness arises from only leveraging model-update consistency among malicious clients within individual training rounds, making the attack effect self-cancel across training rounds. In light of this observation, we propose PoisonedFL, which enforces multi-round consistency among the malicious clients' model updates while not requiring any knowledge about the genuine clients. Our empirical evaluation on five benchmark datasets shows that PoisonedFL breaks eight state-of-the-art defenses and outperforms seven existing model poisoning attacks. Moreover, we also explore new defenses that are tailored to PoisonedFL, but our results show that we can still adapt PoisonedFL to break them. Our study shows that FL systems are considerably less robust than previously thought, underlining the urgency for the development of new defense mechanisms.

Point cloud classification is an essential component in many security-critical applications such as autonomous driving and augmented reality. However, point cloud classifiers are vulnerable to adversarially perturbed point clouds. Existing certified defenses against adversarial point clouds suffer from a key limitation: their certified robustness guarantees are probabilistic, i.e., they produce an incorrect certified robustness guarantee with some probability. In this work, we propose a general framework, namely PointCert, that can transform an arbitrary point cloud classifier to be certifiably robust against adversarial point clouds with deterministic guarantees. PointCert certifiably predicts the same label for a point cloud when the number of arbitrarily added, deleted, and/or modified points is less than a threshold. Moreover, we propose multiple methods to optimize the certified robustness guarantees of PointCert in three application scenarios. We systematically evaluate PointCert on ModelNet and ScanObjectNN benchmark datasets. Our results show that PointCert substantially outperforms state-of-the-art certified defenses even though their robustness guarantees are probabilistic., Comment: CVPR 2023

Encoder as a service is an emerging cloud service. Specifically, a service provider first pre-trains an encoder (i.e., a general-purpose feature extractor) via either supervised learning or self-supervised learning and then deploys it as a cloud service API. A client queries the cloud service API to obtain feature vectors for its training/testing inputs when training/testing its classifier (called downstream classifier). A downstream classifier is vulnerable to adversarial examples, which are testing inputs with carefully crafted perturbation that the downstream classifier misclassifies. Therefore, in safety and security critical applications, a client aims to build a robust downstream classifier and certify its robustness guarantees against adversarial examples. What APIs should the cloud service provide, such that a client can use any certification method to certify the robustness of its downstream classifier against adversarial examples while minimizing the number of queries to the APIs? How can a service provider pre-train an encoder such that clients can build more certifiably robust downstream classifiers? We aim to answer the two questions in this work. For the first question, we show that the cloud service only needs to provide two APIs, which we carefully design, to enable a client to certify the robustness of its downstream classifier with a minimal number of queries to the APIs. For the second question, we show that an encoder pre-trained using a spectral-norm regularization term enables clients to build more robust downstream classifiers., Comment: To appear in Network and Distributed System Security (NDSS) Symposium, 2023

The increasing reliance on Large Language Models (LLMs) across academia and industry necessitates a comprehensive understanding of their robustness to prompts. In response to this vital need, we introduce PromptBench, a robustness benchmark designed to measure LLMs' resilience to adversarial prompts. This study uses a plethora of adversarial textual attacks targeting prompts across multiple levels: character, word, sentence, and semantic. The adversarial prompts, crafted to mimic plausible user errors like typos or synonyms, aim to evaluate how slight deviations can affect LLM outcomes while maintaining semantic integrity. These prompts are then employed in diverse tasks, such as sentiment analysis, natural language inference, reading comprehension, machine translation, and math problem-solving. Our study generates 4788 adversarial prompts, meticulously evaluated over 8 tasks and 13 datasets. Our findings demonstrate that contemporary LLMs are not robust to adversarial prompts. Furthermore, we present comprehensive analysis to understand the mystery behind prompt robustness and its transferability. We then offer insightful robustness analysis and pragmatic recommendations for prompt composition, beneficial to both researchers and everyday users. Code is available at: https://github.com/microsoft/promptbench., Comment: Technical report; code is at: https://github.com/microsoft/promptbench

A generative AI model can generate extremely realistic-looking content, posing growing challenges to the authenticity of information. To address the challenges, watermark has been leveraged to detect AI-generated content. Specifically, a watermark is embedded into an AI-generated content before it is released. A content is detected as AI-generated if a similar watermark can be decoded from it. In this work, we perform a systematic study on the robustness of such watermark-based AI-generated content detection. We focus on AI-generated images. Our work shows that an attacker can post-process a watermarked image via adding a small, human-imperceptible perturbation to it, such that the post-processed image evades detection while maintaining its visual quality. We show the effectiveness of our attack both theoretically and empirically. Moreover, to evade detection, our adversarial post-processing method adds much smaller perturbations to AI-generated images and thus better maintain their visual quality than existing popular post-processing methods such as JPEG compression, Gaussian blur, and Brightness/Contrast. Our work shows the insufficiency of existing watermark-based detection of AI-generated content, highlighting the urgent needs of new methods. Our code is publicly available: https://github.com/zhengyuan-jiang/WEvade., Comment: To appear in ACM Conference on Computer and Communications Security (CCS), 2023

Data poisoning attacks spoof a recommender system to make arbitrary, attacker-desired recommendations via injecting fake users with carefully crafted rating scores into the recommender system. We envision a cat-and-mouse game for such data poisoning attacks and their defenses, i.e., new defenses are designed to defend against existing attacks and new attacks are designed to break them. To prevent such a cat-and-mouse game, we propose PORE, the first framework to build provably robust recommender systems in this work. PORE can transform any existing recommender system to be provably robust against any untargeted data poisoning attacks, which aim to reduce the overall performance of a recommender system. Suppose PORE recommends top-$N$ items to a user when there is no attack. We prove that PORE still recommends at least $r$ of the $N$ items to the user under any data poisoning attack, where $r$ is a function of the number of fake users in the attack. Moreover, we design an efficient algorithm to compute $r$ for each user. We empirically evaluate PORE on popular benchmark datasets., Comment: To appear in USENIX Security Symposium, 2023

Data heterogeneity presents significant challenges for federated learning (FL). Recently, dataset distillation techniques have been introduced, and performed at the client level, to attempt to mitigate some of these challenges. In this paper, we propose a highly efficient FL dataset distillation framework on the server side, significantly reducing both the computational and communication demands on local devices while enhancing the clients' privacy. Unlike previous strategies that perform dataset distillation on local devices and upload synthetic data to the server, our technique enables the server to leverage prior knowledge from pre-trained deep generative models to synthesize essential data representations from a heterogeneous model architecture. This process allows local devices to train smaller surrogate models while enabling the training of a larger global model on the server, effectively minimizing resource utilization. We substantiate our claim with a theoretical analysis, demonstrating the asymptotic resemblance of the process to the hypothetical ideal of completely centralized training on a heterogeneous dataset. Empirical evidence from our comprehensive experiments indicates our method's superiority, delivering an accuracy enhancement of up to 40% over non-dataset-distillation techniques in highly heterogeneous FL contexts, and surpassing existing dataset-distillation methods by 18%. In addition to the high accuracy, our framework converges faster than the baselines because rather than the server trains on several sets of heterogeneous data distributions, it trains on a multi-modal distribution. Our code is available at https://github.com/FedDG23/FedDG-main.git

Decentralized federated learning (DFL) enables clients (e.g., hospitals and banks) to jointly train machine learning models without a central orchestration server. In each global training round, each client trains a local model on its own training data and then they exchange local models for aggregation. In this work, we propose SelfishAttack, a new family of attacks to DFL. In SelfishAttack, a set of selfish clients aim to achieve competitive advantages over the remaining non-selfish ones, i.e., the final learnt local models of the selfish clients are more accurate than those of the non-selfish ones. Towards this goal, the selfish clients send carefully crafted local models to each remaining non-selfish one in each global training round. We formulate finding such local models as an optimization problem and propose methods to solve it when DFL uses different aggregation rules. Theoretically, we show that our methods find the optimal solutions to the optimization problem. Empirically, we show that SelfishAttack successfully increases the accuracy gap (i.e., competitive advantage) between the final learnt local models of selfish clients and those of non-selfish ones. Moreover, SelfishAttack achieves larger accuracy gaps than poisoning attacks when extended to increase competitive advantages.

A prompt injection attack aims to inject malicious instruction/data into the input of an LLM-Integrated Application such that it produces results as an attacker desires. Existing works are limited to case studies. As a result, the literature lacks a systematic understanding of prompt injection attacks and their defenses. We aim to bridge the gap in this work. In particular, we propose a framework to formalize prompt injection attacks. Existing attacks are special cases in our framework. Moreover, based on our framework, we design a new attack by combining existing ones. Using our framework, we conduct a systematic evaluation on 5 prompt injection attacks and 10 defenses with 10 LLMs and 7 tasks. Our work provides a common benchmark for quantitatively evaluating future prompt injection attacks and defenses. To facilitate research on this topic, we make our platform public at https://github.com/liu00222/Open-Prompt-Injection., Comment: To appear in USENIX Security Symposium 2024

Large language models (LLMs) have garnered significant attention due to their impressive natural language processing (NLP) capabilities. Recently, many studies have focused on the tool utilization ability of LLMs. They primarily investigated how LLMs effectively collaborate with given specific tools. However, in scenarios where LLMs serve as intelligent agents, as seen in applications like AutoGPT and MetaGPT, LLMs are expected to engage in intricate decision-making processes that involve deciding whether to employ a tool and selecting the most suitable tool(s) from a collection of available tools to fulfill user requests. Therefore, in this paper, we introduce MetaTool, a benchmark designed to evaluate whether LLMs have tool usage awareness and can correctly choose tools. Specifically, we create a dataset called ToolE within the benchmark. This dataset contains various types of user queries in the form of prompts that trigger LLMs to use tools, including both single-tool and multi-tool scenarios. Subsequently, we set the tasks for both tool usage awareness and tool selection. We define four subtasks from different perspectives in tool selection, including tool selection with similar choices, tool selection in specific scenarios, tool selection with possible reliability issues, and multi-tool selection. We conduct experiments involving eight popular LLMs and find that the majority of them still struggle to effectively select tools, highlighting the existing gaps between LLMs and genuine intelligent agents. However, through the error analysis, we found there is still significant room for improvement. Finally, we conclude with insights for tool developers -- we strongly recommend that tool developers choose an appropriate rewrite model for generating new descriptions based on the downstream LLM the tool will apply to. Our code is in https://github.com/HowieHwong/MetaTool.

Large language models (LLMs) have achieved remarkable performance in various evaluation benchmarks. However, concerns are raised about potential data contamination in their considerable volume of training corpus. Moreover, the static nature and fixed complexity of current benchmarks may inadequately gauge the advancing capabilities of LLMs. In this paper, we introduce DyVal, a general and flexible protocol for dynamic evaluation of LLMs. Based on our framework, we build graph-informed DyVal by leveraging the structural advantage of directed acyclic graphs to dynamically generate evaluation samples with controllable complexities. DyVal generates challenging evaluation sets on reasoning tasks including mathematics, logical reasoning, and algorithm problems. We evaluate various LLMs ranging from Flan-T5-large to GPT-3.5-Turbo and GPT-4. Experiments show that LLMs perform worse in DyVal-generated evaluation samples with different complexities, highlighting the significance of dynamic evaluation. We also analyze the failure cases and results of different prompting methods. Moreover, DyVal-generated samples are not only evaluation sets, but also helpful data for fine-tuning to improve the performance of LLMs on existing benchmarks. We hope that DyVal can shed light on future evaluation research of LLMs. Code is available at: https://github.com/microsoft/promptbench., Comment: ICLR 2024 spotlight; 38 pages; code is at aka.ms/dyval

With rich visual data, such as images, becoming readily associated with items, visually-aware recommendation systems (VARS) have been widely used in different applications. Recent studies have shown that VARS are vulnerable to item-image adversarial attacks, which add human-imperceptible perturbations to the clean images associated with those items. Attacks on VARS pose new security challenges to a wide range of applications such as e-Commerce and social networks where VARS are widely used. How to secure VARS from such adversarial attacks becomes a critical problem. Currently, there is still a lack of systematic study on how to design secure defense strategies against visual attacks on VARS. In this paper, we attempt to fill this gap by proposing an adversarial image reconstruction and detection framework to secure VARS. Our proposed method can simultaneously (1) secure VARS from adversarial attacks characterized by local perturbations by image reconstruction based on global vision transformers; and (2) accurately detect adversarial examples using a novel contrastive learning approach. Meanwhile, our framework is designed to be used as both a filter and a detector so that they can be jointly trained to improve the flexibility of our defense strategy to a variety of attacks and VARS models. We have conducted extensive experimental studies with two popular attack methods (FGSM and PGD). Our experimental results on two real-world datasets show that our defense strategy against visual attacks is effective and outperforms existing methods on different attacks. Moreover, our method can detect adversarial examples with high accuracy.

Federated learning (FL) is an emerging machine learning paradigm, in which clients jointly learn a model with the help of a cloud server. A fundamental challenge of FL is that the clients are often heterogeneous, e.g., they have different computing powers, and thus the clients may send model updates to the server with substantially different delays. Asynchronous FL aims to address this challenge by enabling the server to update the model once any client's model update reaches it without waiting for other clients' model updates. However, like synchronous FL, asynchronous FL is also vulnerable to poisoning attacks, in which malicious clients manipulate the model via poisoning their local data and/or model updates sent to the server. Byzantine-robust FL aims to defend against poisoning attacks. In particular, Byzantine-robust FL can learn an accurate model even if some clients are malicious and have Byzantine behaviors. However, most existing studies on Byzantine-robust FL focused on synchronous FL, leaving asynchronous FL largely unexplored. In this work, we bridge this gap by proposing AFLGuard, a Byzantine-robust asynchronous FL method. We show that, both theoretically and empirically, AFLGuard is robust against various existing and adaptive poisoning attacks (both untargeted and targeted). Moreover, AFLGuard outperforms existing Byzantine-robust asynchronous FL methods., Comment: Accepted by ACSAC 2022

Classifiers in supervised learning have various security and privacy issues, e.g., 1) data poisoning attacks, backdoor attacks, and adversarial examples on the security side as well as 2) inference attacks and the right to be forgotten for the training data on the privacy side. Various secure and privacy-preserving supervised learning algorithms with formal guarantees have been proposed to address these issues. However, they suffer from various limitations such as accuracy loss, small certified security guarantees, and/or inefficiency. Self-supervised learning is an emerging technique to pre-train encoders using unlabeled data. Given a pre-trained encoder as a feature extractor, supervised learning can train a simple yet accurate classifier using a small amount of labeled training data. In this work, we perform the first systematic, principled measurement study to understand whether and when a pre-trained encoder can address the limitations of secure or privacy-preserving supervised learning algorithms. Our key findings are that a pre-trained encoder substantially improves 1) both accuracy under no attacks and certified security guarantees against data poisoning and backdoor attacks of state-of-the-art secure learning algorithms (i.e., bagging and KNN), 2) certified security guarantees of randomized smoothing against adversarial examples without sacrificing its accuracy under no attacks, 3) accuracy of differentially private classifiers, and 4) accuracy and/or efficiency of exact machine unlearning.

Contrastive learning (CL) pre-trains general-purpose encoders using an unlabeled pre-training dataset, which consists of images or image-text pairs. CL is vulnerable to data poisoning based backdoor attacks (DPBAs), in which an attacker injects poisoned inputs into the pre-training dataset so the encoder is backdoored. However, existing DPBAs achieve limited effectiveness. In this work, we take the first step to analyze the limitations of existing backdoor attacks and propose new DPBAs called CorruptEncoder to CL. CorruptEncoder introduces a new attack strategy to create poisoned inputs and uses a theory-guided method to maximize attack effectiveness. Our experiments show that CorruptEncoder substantially outperforms existing DPBAs. In particular, CorruptEncoder is the first DPBA that achieves more than 90% attack success rates with only a few (3) reference images and a small poisoning ratio 0.5%. Moreover, we also propose a defense, called localized cropping, to defend against DPBAs. Our results show that our defense can reduce the effectiveness of DPBAs, but it sacrifices the utility of the encoder, highlighting the need for new defenses., Comment: CVPR 2024

Federated learning (FL) allows multiple clients to collaboratively train a deep learning model. One major challenge of FL is when data distribution is heterogeneous, i.e., differs from one client to another. Existing personalized FL algorithms are only applicable to narrow cases, e.g., one or two data classes per client, and therefore they do not satisfactorily address FL under varying levels of data heterogeneity. In this paper, we propose a novel framework, called DisTrans, to improve FL performance (i.e., model accuracy) via train and test-time distributional transformations along with a double-input-channel model structure. DisTrans works by optimizing distributional offsets and models for each FL client to shift their data distribution, and aggregates these offsets at the FL server to further improve performance in case of distributional heterogeneity. Our evaluation on multiple benchmark datasets shows that DisTrans outperforms state-of-the-art FL methods and data augmentation methods under various settings and different degrees of client distributional heterogeneity., Comment: In the Proceedings of European Conference on Computer Vision (ECCV), 2022

Federated learning is vulnerable to poisoning attacks in which malicious clients poison the global model via sending malicious model updates to the server. Existing defenses focus on preventing a small number of malicious clients from poisoning the global model via robust federated learning methods and detecting malicious clients when there are a large number of them. However, it is still an open challenge how to recover the global model from poisoning attacks after the malicious clients are detected. A naive solution is to remove the detected malicious clients and train a new global model from scratch, which incurs large cost that may be intolerable for resource-constrained clients such as smartphones and IoT devices. In this work, we propose FedRecover, which can recover an accurate global model from poisoning attacks with small cost for the clients. Our key idea is that the server estimates the clients' model updates instead of asking the clients to compute and communicate them during the recovery process. In particular, the server stores the global models and clients' model updates in each round, when training the poisoned global model. During the recovery process, the server estimates a client's model update in each round using its stored historical information. Moreover, we further optimize FedRecover to recover a more accurate global model using warm-up, periodic correction, abnormality fixing, and final tuning strategies, in which the server asks the clients to compute and communicate their exact model updates. Theoretically, we show that the global model recovered by FedRecover is close to or the same as that recovered by train-from-scratch under some assumptions. Empirically, our evaluation on four datasets, three federated learning methods, as well as untargeted and targeted poisoning attacks (e.g., backdoor attacks) shows that FedRecover is both accurate and efficient., Comment: To appear in IEEE S&P 2023

Multi-label classification, which predicts a set of labels for an input, has many applications. However, multiple recent studies showed that multi-label classification is vulnerable to adversarial examples. In particular, an attacker can manipulate the labels predicted by a multi-label classifier for an input via adding carefully crafted, human-imperceptible perturbation to it. Existing provable defenses for multi-class classification achieve sub-optimal provable robustness guarantees when generalized to multi-label classification. In this work, we propose MultiGuard, the first provably robust defense against adversarial examples to multi-label classification. Our MultiGuard leverages randomized smoothing, which is the state-of-the-art technique to build provably robust classifiers. Specifically, given an arbitrary multi-label classifier, our MultiGuard builds a smoothed multi-label classifier via adding random noise to the input. We consider isotropic Gaussian noise in this work. Our major theoretical contribution is that we show a certain number of ground truth labels of an input are provably in the set of labels predicted by our MultiGuard when the $\ell_2$-norm of the adversarial perturbation added to the input is bounded. Moreover, we design an algorithm to compute our provable robustness guarantees. Empirically, we evaluate our MultiGuard on VOC 2007, MS-COCO, and NUS-WIDE benchmark datasets. Our code is available at: \url{https://github.com/quwenjie/MultiGuard}, Comment: Accepted by NeurIPS 2022

Due to its distributed nature, federated learning is vulnerable to poisoning attacks, in which malicious clients poison the training process via manipulating their local training data and/or local model updates sent to the cloud server, such that the poisoned global model misclassifies many indiscriminate test inputs or attacker-chosen ones. Existing defenses mainly leverage Byzantine-robust federated learning methods or detect malicious clients. However, these defenses do not have provable security guarantees against poisoning attacks and may be vulnerable to more advanced attacks. In this work, we aim to bridge the gap by proposing FLCert, an ensemble federated learning framework, that is provably secure against poisoning attacks with a bounded number of malicious clients. Our key idea is to divide the clients into groups, learn a global model for each group of clients using any existing federated learning method, and take a majority vote among the global models to classify a test input. Specifically, we consider two methods to group the clients and propose two variants of FLCert correspondingly, i.e., FLCert-P that randomly samples clients in each group, and FLCert-D that divides clients to disjoint groups deterministically. Our extensive experiments on multiple datasets show that the label predicted by our FLCert for a test input is provably unaffected by a bounded number of malicious clients, no matter what poisoning attacks they use., Comment: To appear in Transactions on Information Forensics and Security. arXiv admin note: text overlap with arXiv:2102.01854

Semi-supervised learning (SSL) leverages both labeled and unlabeled data to train machine learning (ML) models. State-of-the-art SSL methods can achieve comparable performance to supervised learning by leveraging much fewer labeled data. However, most existing works focus on improving the performance of SSL. In this work, we take a different angle by studying the training data privacy of SSL. Specifically, we propose the first data augmentation-based membership inference attacks against ML models trained by SSL. Given a data sample and the black-box access to a model, the goal of membership inference attack is to determine whether the data sample belongs to the training dataset of the model. Our evaluation shows that the proposed attack can consistently outperform existing membership inference attacks and achieves the best performance against the model trained by SSL. Moreover, we uncover that the reason for membership leakage in SSL is different from the commonly believed one in supervised learning, i.e., overfitting (the gap between training and testing accuracy). We observe that the SSL model is well generalized to the testing data (with almost 0 overfitting) but ''memorizes'' the training data by giving a more confident prediction regardless of its correctness. We also explore early stopping as a countermeasure to prevent membership inference attacks against SSL. The results show that early stopping can mitigate the membership inference attack, but with the cost of model's utility degradation., Comment: Accepted to ECCV 2022

Federated learning (FL) is vulnerable to model poisoning attacks, in which malicious clients corrupt the global model via sending manipulated model updates to the server. Existing defenses mainly rely on Byzantine-robust FL methods, which aim to learn an accurate global model even if some clients are malicious. However, they can only resist a small number of malicious clients in practice. It is still an open challenge how to defend against model poisoning attacks with a large number of malicious clients. Our FLDetector addresses this challenge via detecting malicious clients. FLDetector aims to detect and remove the majority of the malicious clients such that a Byzantine-robust FL method can learn an accurate global model using the remaining clients. Our key observation is that, in model poisoning attacks, the model updates from a client in multiple iterations are inconsistent. Therefore, FLDetector detects malicious clients via checking their model-updates consistency. Roughly speaking, the server predicts a client's model update in each iteration based on its historical model updates using the Cauchy mean value theorem and L-BFGS, and flags a client as malicious if the received model update from the client and the predicted model update are inconsistent in multiple iterations. Our extensive experiments on three benchmark datasets show that FLDetector can accurately detect malicious clients in multiple state-of-the-art model poisoning attacks. After removing the detected malicious clients, existing Byzantine-robust FL methods can learn accurate global models.Our code is available at https://github.com/zaixizhang/FLDetector., Comment: Accepted by KDD 2022 (Research Track)

Although local differential privacy (LDP) protects individual users' data from inference by an untrusted data curator, recent studies show that an attacker can launch a data poisoning attack from the user side to inject carefully-crafted bogus data into the LDP protocols in order to maximally skew the final estimate by the data curator. In this work, we further advance this knowledge by proposing a new fine-grained attack, which allows the attacker to fine-tune and simultaneously manipulate mean and variance estimations that are popular analytical tasks for many real-world applications. To accomplish this goal, the attack leverages the characteristics of LDP to inject fake data into the output domain of the local LDP instance. We call our attack the output poisoning attack (OPA). We observe a security-privacy consistency where a small privacy loss enhances the security of LDP, which contradicts the known security-privacy trade-off from prior work. We further study the consistency and reveal a more holistic view of the threat landscape of data poisoning attacks on LDP. We comprehensively evaluate our attack against a baseline attack that intuitively provides false input to LDP. The experimental results show that OPA outperforms the baseline on three real-world datasets. We also propose a novel defense method that can recover the result accuracy from polluted data collection and offer insight into the secure LDP design.

Contrastive learning pre-trains an image encoder using a large amount of unlabeled data such that the image encoder can be used as a general-purpose feature extractor for various downstream tasks. In this work, we propose PoisonedEncoder, a data poisoning attack to contrastive learning. In particular, an attacker injects carefully crafted poisoning inputs into the unlabeled pre-training data, such that the downstream classifiers built based on the poisoned encoder for multiple target downstream tasks simultaneously classify attacker-chosen, arbitrary clean inputs as attacker-chosen, arbitrary classes. We formulate our data poisoning attack as a bilevel optimization problem, whose solution is the set of poisoning inputs; and we propose a contrastive-learning-tailored method to approximately solve it. Our evaluation on multiple datasets shows that PoisonedEncoder achieves high attack success rates while maintaining the testing accuracy of the downstream classifiers built upon the poisoned encoder for non-attacker-chosen inputs. We also evaluate five defenses against PoisonedEncoder, including one pre-processing, three in-processing, and one post-processing defenses. Our results show that these defenses can decrease the attack success rate of PoisonedEncoder, but they also sacrifice the utility of the encoder or require a large clean pre-training dataset., Comment: USENIX Security Symposium, 2022

Existing model poisoning attacks to federated learning assume that an attacker has access to a large fraction of compromised genuine clients. However, such assumption is not realistic in production federated learning systems that involve millions of clients. In this work, we propose the first Model Poisoning Attack based on Fake clients called MPAF. Specifically, we assume the attacker injects fake clients to a federated learning system and sends carefully crafted fake local model updates to the cloud server during training, such that the learnt global model has low accuracy for many indiscriminate test inputs. Towards this goal, our attack drags the global model towards an attacker-chosen base model that has low accuracy. Specifically, in each round of federated learning, the fake clients craft fake local model updates that point to the base model and scale them up to amplify their impact before sending them to the cloud server. Our experiments show that MPAF can significantly decrease the test accuracy of the global model, even if classical defenses and norm clipping are adopted, highlighting the need for more advanced defenses., Comment: In CVPR Workshops, 2022

Cross-device tracking has drawn growing attention from both commercial companies and the general public because of its privacy implications and applications for user profiling, personalized services, etc. One particular, wide-used type of cross-device tracking is to leverage browsing histories of user devices, e.g., characterized by a list of IP addresses used by the devices and domains visited by the devices. However, existing browsing history based methods have three drawbacks. First, they cannot capture latent correlations among IPs and domains. Second, their performance degrades significantly when labeled device pairs are unavailable. Lastly, they are not robust to uncertainties in linking browsing histories to devices. We propose GraphTrack, a graph-based cross-device tracking framework, to track users across different devices by correlating their browsing histories. Specifically, we propose to model the complex interplays among IPs, domains, and devices as graphs and capture the latent correlations between IPs and between domains. We construct graphs that are robust to uncertainties in linking browsing histories to devices. Moreover, we adapt random walk with restart to compute similarity scores between devices based on the graphs. GraphTrack leverages the similarity scores to perform cross-device tracking. GraphTrack does not require labeled device pairs and can incorporate them if available. We evaluate GraphTrack on two real-world datasets, i.e., a publicly available mobile-desktop tracking dataset (around 100 users) and a multiple-device tracking dataset (154K users) we collected. Our results show that GraphTrack substantially outperforms the state-of-the-art on both datasets., Comment: Accepted by AsiaCCS'22

Pre-trained encoders are general-purpose feature extractors that can be used for many downstream tasks. Recent progress in self-supervised learning can pre-train highly effective encoders using a large volume of unlabeled data, leading to the emerging encoder as a service (EaaS). A pre-trained encoder may be deemed confidential because its training requires lots of data and computation resources as well as its public release may facilitate misuse of AI, e.g., for deepfakes generation. In this paper, we propose the first attack called StolenEncoder to steal pre-trained image encoders. We evaluate StolenEncoder on multiple target encoders pre-trained by ourselves and three real-world target encoders including the ImageNet encoder pre-trained by Google, CLIP encoder pre-trained by OpenAI, and Clarifai's General Embedding encoder deployed as a paid EaaS. Our results show that our stolen encoders have similar functionality with the target encoders. In particular, the downstream classifiers built upon a target encoder and a stolen one have similar accuracy. Moreover, stealing a target encoder using StolenEncoder requires much less data and computation resources than pre-training it from scratch. We also explore three defenses that perturb feature vectors produced by a target encoder. Our results show these defenses are not enough to mitigate StolenEncoder., Comment: To appear in ACM Conference on Computer and Communications Security (CCS), 2022

With the recent demand of deploying neural network models on mobile and edge devices, it is desired to improve the model's generalizability on unseen testing data, as well as enhance the model's robustness under fixed-point quantization for efficient deployment. Minimizing the training loss, however, provides few guarantees on the generalization and quantization performance. In this work, we fulfill the need of improving generalization and quantization performance simultaneously by theoretically unifying them under the framework of improving the model's robustness against bounded weight perturbation and minimizing the eigenvalues of the Hessian matrix with respect to model weights. We therefore propose HERO, a Hessian-enhanced robust optimization method, to minimize the Hessian eigenvalues through a gradient-based training process, simultaneously improving the generalization and quantization performance. HERO enables up to a 3.8% gain on test accuracy, up to 30% higher accuracy under 80% training label perturbation, and the best post-training quantization accuracy across a wide range of precision, including a >10% accuracy improvement over SGD-trained models for common model architectures on various datasets.

Local Differential Privacy (LDP) protocols enable an untrusted server to perform privacy-preserving, federated data analytics. Various LDP protocols have been developed for different types of data such as categorical data, numerical data, and key-value data. Due to their distributed settings, LDP protocols are fundamentally vulnerable to poisoning attacks, in which fake users manipulate the server's analytics results via sending carefully crafted data to the server. However, existing poisoning attacks focused on LDP protocols for simple data types such as categorical and numerical data, leaving the security of LDP protocols for more advanced data types such as key-value data unexplored. In this work, we aim to bridge the gap by introducing novel poisoning attacks to LDP protocols for key-value data. In such a LDP protocol, a server aims to simultaneously estimate the frequency and mean value of each key among some users, each of whom possesses a set of key-value pairs. Our poisoning attacks aim to simultaneously maximize the frequencies and mean values of some attacker-chosen target keys via sending carefully crafted data from some fake users to the sever. Specifically, since our attacks have two objectives, we formulate them as a two-objective optimization problem. Moreover, we propose a method to approximately solve the two-objective optimization problem, from which we obtain the optimal crafted data the fake users should send to the server. We demonstrate the effectiveness of our attacks to three LDP protocols for key-value data both theoretically and empirically. We also explore two defenses against our attacks, which are effective in some scenarios but have limited effectiveness in other scenarios. Our results highlight the needs for new defenses against our poisoning attacks., Comment: To appear in USENIX Security Symposium, 2022

Foundation models--such as GPT, CLIP, and DINO--have achieved revolutionary progress in the past several years and are commonly believed to be a promising approach for general-purpose AI. In particular, self-supervised learning is adopted to pre-train a foundation model using a large amount of unlabeled data. A pre-trained foundation model is like an ``operating system'' of the AI ecosystem. Specifically, a foundation model can be used as a feature extractor for many downstream tasks with little or no labeled training data. Existing studies on foundation models mainly focused on pre-training a better foundation model to improve its performance on downstream tasks in non-adversarial settings, leaving its security and privacy in adversarial settings largely unexplored. A security or privacy issue of a pre-trained foundation model leads to a single point of failure for the AI ecosystem. In this book chapter, we discuss 10 basic security and privacy problems for the pre-trained foundation models, including six confidentiality problems, three integrity problems, and one availability problem. For each problem, we discuss potential opportunities and challenges. We hope our book chapter will inspire future research on the security and privacy of foundation models., Comment: A book chapter

Existing deepfake-detection methods focus on passive detection, i.e., they detect fake face images via exploiting the artifacts produced during deepfake manipulation. A key limitation of passive detection is that it cannot detect fake faces that are generated by new deepfake generation methods. In this work, we propose FaceGuard, a proactive deepfake-detection framework. FaceGuard embeds a watermark into a real face image before it is published on social media. Given a face image that claims to be an individual (e.g., Nicolas Cage), FaceGuard extracts a watermark from it and predicts the face image to be fake if the extracted watermark does not match well with the individual's ground truth one. A key component of FaceGuard is a new deep-learning-based watermarking method, which is 1) robust to normal image post-processing such as JPEG compression, Gaussian blurring, cropping, and resizing, but 2) fragile to deepfake manipulation. Our evaluation on multiple datasets shows that FaceGuard can detect deepfakes accurately and outperforms existing methods.

Given a set of unlabeled images or (image, text) pairs, contrastive learning aims to pre-train an image encoder that can be used as a feature extractor for many downstream tasks. In this work, we propose EncoderMI, the first membership inference method against image encoders pre-trained by contrastive learning. In particular, given an input and a black-box access to an image encoder, EncoderMI aims to infer whether the input is in the training dataset of the image encoder. EncoderMI can be used 1) by a data owner to audit whether its (public) data was used to pre-train an image encoder without its authorization or 2) by an attacker to compromise privacy of the training data when it is private/sensitive. Our EncoderMI exploits the overfitting of the image encoder towards its training data. In particular, an overfitted image encoder is more likely to output more (or less) similar feature vectors for two augmented versions of an input in (or not in) its training dataset. We evaluate EncoderMI on image encoders pre-trained on multiple datasets by ourselves as well as the Contrastive Language-Image Pre-training (CLIP) image encoder, which is pre-trained on 400 million (image, text) pairs collected from the Internet and released by OpenAI. Our results show that EncoderMI can achieve high accuracy, precision, and recall. We also explore a countermeasure against EncoderMI via preventing overfitting through early stopping. Our results show that it achieves trade-offs between accuracy of EncoderMI and utility of the image encoder, i.e., it can reduce the accuracy of EncoderMI, but it also incurs classification accuracy loss of the downstream classifiers built based on the image encoder., Comment: To appear in ACM Conference on Computer and Communications Security (CCS), 2021

Self-supervised learning in computer vision aims to pre-train an image encoder using a large amount of unlabeled images or (image, text) pairs. The pre-trained image encoder can then be used as a feature extractor to build downstream classifiers for many downstream tasks with a small amount of or no labeled training data. In this work, we propose BadEncoder, the first backdoor attack to self-supervised learning. In particular, our BadEncoder injects backdoors into a pre-trained image encoder such that the downstream classifiers built based on the backdoored image encoder for different downstream tasks simultaneously inherit the backdoor behavior. We formulate our BadEncoder as an optimization problem and we propose a gradient descent based method to solve it, which produces a backdoored image encoder from a clean one. Our extensive empirical evaluation results on multiple datasets show that our BadEncoder achieves high attack success rates while preserving the accuracy of the downstream classifiers. We also show the effectiveness of BadEncoder using two publicly available, real-world image encoders, i.e., Google's image encoder pre-trained on ImageNet and OpenAI's Contrastive Language-Image Pre-training (CLIP) image encoder pre-trained on 400 million (image, text) pairs collected from the Internet. Moreover, we consider defenses including Neural Cleanse and MNTD (empirical defenses) as well as PatchGuard (a provable defense). Our results show that these defenses are insufficient to defend against BadEncoder, highlighting the needs for new defenses against our BadEncoder. Our code is publicly available at: https://github.com/jjy1994/BadEncoder., Comment: To appear in IEEE Symposium on Security and Privacy, 2022

Deepfakes pose growing challenges to the trust of information on the Internet. Thus, detecting deepfakes has attracted increasing attentions from both academia and industry. State-of-the-art deepfake detection methods consist of two key components, i.e., face extractor and face classifier, which extract the face region in an image and classify it to be real/fake, respectively. Existing studies mainly focused on improving the detection performance in non-adversarial settings, leaving security of deepfake detection in adversarial settings largely unexplored. In this work, we aim to bridge the gap. In particular, we perform a systematic measurement study to understand the security of the state-of-the-art deepfake detection methods in adversarial settings. We use two large-scale public deepfakes data sources including FaceForensics++ and Facebook Deepfake Detection Challenge, where the deepfakes are fake face images; and we train state-of-the-art deepfake detection methods. These detection methods can achieve 0.94--0.99 accuracies in non-adversarial settings on these datasets. However, our measurement results uncover multiple security limitations of the deepfake detection methods in adversarial settings. First, we find that an attacker can evade a face extractor, i.e., the face extractor fails to extract the correct face regions, via adding small Gaussian noise to its deepfake images. Second, we find that a face classifier trained using deepfakes generated by one method cannot detect deepfakes generated by another method, i.e., an attacker can evade detection via generating deepfakes using a new method. Third, we find that an attacker can leverage backdoor attacks developed by the adversarial machine learning community to evade a face classifier. Our results highlight that deepfake detection should consider the adversarial nature of the problem., Comment: To appear in ICDF2C 2021

Self-attention has become increasingly popular in a variety of sequence modeling tasks from natural language processing to recommendation, due to its effectiveness. However, self-attention suffers from quadratic computational and memory complexities, prohibiting its applications on long sequences. Existing approaches that address this issue mainly rely on a sparse attention context, either using a local window, or a permuted bucket obtained by locality-sensitive hashing (LSH) or sorting, while crucial information may be lost. Inspired by the idea of vector quantization that uses cluster centroids to approximate items, we propose LISA (LInear-time Self Attention), which enjoys both the effectiveness of vanilla self-attention and the efficiency of sparse attention. LISA scales linearly with the sequence length, while enabling full contextual attention via computing differentiable histograms of codeword distributions. Meanwhile, unlike some efficient attention methods, our method poses no restriction on casual masking or sequence length. We evaluate our method on four real-world datasets for sequential recommendation. The results show that LISA outperforms the state-of-the-art efficient attention methods in both performance and speed; and it is up to 57x faster and 78x more memory efficient than vanilla self-attention., Comment: 11 pages. Accepted by the Web Conference 2021 (WWW '21)

Sequential recommendation plays an increasingly important role in many e-commerce services such as display advertisement and online shopping. With the rapid development of these services in the last two decades, users have accumulated a massive amount of behavior data. Richer sequential behavior data has been proven to be of great value for sequential recommendation. However, traditional sequential models fail to handle users' lifelong sequences, as their linear computational and storage cost prohibits them from performing online inference. Recently, lifelong sequential modeling methods that borrow the idea of memory networks from NLP are proposed to address this issue. However, the RNN-based memory networks built upon intrinsically suffer from the inability to capture long-term dependencies and may instead be overwhelmed by the noise on extremely long behavior sequences. In addition, as the user's behavior sequence gets longer, more interests would be demonstrated in it. It is therefore crucial to model and capture the diverse interests of users. In order to tackle these issues, we propose a novel lifelong incremental multi-interest self attention based sequential recommendation model, namely LimaRec. Our proposed method benefits from the carefully designed self-attention to identify relevant information from users' behavior sequences with different interests. It is still able to incrementally update users' representations for online inference, similarly to memory network based approaches. We extensively evaluate our method on four real-world datasets and demonstrate its superior performances compared to the state-of-the-art baselines., Comment: 11 pages

3D point cloud classification has many safety-critical applications such as autonomous driving and robotic grasping. However, several studies showed that it is vulnerable to adversarial attacks. In particular, an attacker can make a classifier predict an incorrect label for a 3D point cloud via carefully modifying, adding, and/or deleting a small number of its points. Randomized smoothing is state-of-the-art technique to build certifiably robust 2D image classifiers. However, when applied to 3D point cloud classification, randomized smoothing can only certify robustness against adversarially modified points. In this work, we propose PointGuard, the first defense that has provable robustness guarantees against adversarially modified, added, and/or deleted points. Specifically, given a 3D point cloud and an arbitrary point cloud classifier, our PointGuard first creates multiple subsampled point clouds, each of which contains a random subset of the points in the original point cloud; then our PointGuard predicts the label of the original point cloud as the majority vote among the labels of the subsampled point clouds predicted by the point cloud classifier. Our first major theoretical contribution is that we show PointGuard provably predicts the same label for a 3D point cloud when the number of adversarially modified, added, and/or deleted points is bounded. Our second major theoretical contribution is that we prove the tightness of our derived bound when no assumptions on the point cloud classifier are made. Moreover, we design an efficient algorithm to compute our certified robustness guarantees. We also empirically evaluate PointGuard on ModelNet40 and ScanNet benchmark datasets., Comment: Published in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021

A key challenge of big data analytics is how to collect a large volume of (labeled) data. Crowdsourcing aims to address this challenge via aggregating and estimating high-quality data (e.g., sentiment label for text) from pervasive clients/users. Existing studies on crowdsourcing focus on designing new methods to improve the aggregated data quality from unreliable/noisy clients. However, the security aspects of such crowdsourcing systems remain under-explored to date. We aim to bridge this gap in this work. Specifically, we show that crowdsourcing is vulnerable to data poisoning attacks, in which malicious clients provide carefully crafted data to corrupt the aggregated data. We formulate our proposed data poisoning attacks as an optimization problem that maximizes the error of the aggregated data. Our evaluation results on one synthetic and two real-world benchmark datasets demonstrate that the proposed attacks can substantially increase the estimation errors of the aggregated data. We also propose two defenses to reduce the impact of malicious clients. Our empirical results show that the proposed defenses can substantially reduce the estimation errors of the data poisoning attacks., Comment: To appear in the Web Conference 2021 (WWW '21)

Federated learning enables clients to collaboratively learn a shared global model without sharing their local training data with a cloud server. However, malicious clients can corrupt the global model to predict incorrect labels for testing examples. Existing defenses against malicious clients leverage Byzantine-robust federated learning methods. However, these methods cannot provably guarantee that the predicted label for a testing example is not affected by malicious clients. We bridge this gap via ensemble federated learning. In particular, given any base federated learning algorithm, we use the algorithm to learn multiple global models, each of which is learnt using a randomly selected subset of clients. When predicting the label of a testing example, we take majority vote among the global models. We show that our ensemble federated learning with any base federated learning algorithm is provably secure against malicious clients. Specifically, the label predicted by our ensemble global model for a testing example is provably not affected by a bounded number of malicious clients. Moreover, we show that our derived bound is tight. We evaluate our method on MNIST and Human Activity Recognition datasets. For instance, our method can achieve a certified accuracy of 88% on MNIST when 20 out of 1,000 clients are malicious., Comment: Accepted by AAAI-21. For slides, see https://people.duke.edu/~zg70/code/Secure_Federated_Learning.pdf . For the talk, see https://www.youtube.com/watch?v=LP4uqW18yA0

Membership inference (MI) attacks affect user privacy by inferring whether given data samples have been used to train a target learning model, e.g., a deep neural network. There are two types of MI attacks in the literature, i.e., these with and without shadow models. The success of the former heavily depends on the quality of the shadow model, i.e., the transferability between the shadow and the target; the latter, given only blackbox probing access to the target model, cannot make an effective inference of unknowns, compared with MI attacks using shadow models, due to the insufficient number of qualified samples labeled with ground truth membership information. In this paper, we propose an MI attack, called BlindMI, which probes the target model and extracts membership semantics via a novel approach, called differential comparison. The high-level idea is that BlindMI first generates a dataset with nonmembers via transforming existing samples into new samples, and then differentially moves samples from a target dataset to the generated, non-member set in an iterative manner. If the differential move of a sample increases the set distance, BlindMI considers the sample as non-member and vice versa. BlindMI was evaluated by comparing it with state-of-the-art MI attack algorithms. Our evaluation shows that BlindMI improves F1-score by nearly 20% when compared to state-of-the-art on some datasets, such as Purchase-50 and Birds-200, in the blind setting where the adversary does not know the target model's architecture and the target dataset's ground truth labels. We also show that BlindMI can defeat state-of-the-art defenses.

Recommender systems play a crucial role in helping users to find their interested information in various web services such as Amazon, YouTube, and Google News. Various recommender systems, ranging from neighborhood-based, association-rule-based, matrix-factorization-based, to deep learning based, have been developed and deployed in industry. Among them, deep learning based recommender systems become increasingly popular due to their superior performance. In this work, we conduct the first systematic study on data poisoning attacks to deep learning based recommender systems. An attacker's goal is to manipulate a recommender system such that the attacker-chosen target items are recommended to many users. To achieve this goal, our attack injects fake users with carefully crafted ratings to a recommender system. Specifically, we formulate our attack as an optimization problem, such that the injected ratings would maximize the number of normal users to whom the target items are recommended. However, it is challenging to solve the optimization problem because it is a non-convex integer programming problem. To address the challenge, we develop multiple techniques to approximately solve the optimization problem. Our experimental results on three real-world datasets, including small and large datasets, show that our attack is effective and outperforms existing attacks. Moreover, we attempt to detect fake users via statistical analysis of the rating patterns of normal and fake users. Our results show that our attack is still effective and outperforms existing attacks even if such a detector is deployed., Comment: To appear in NDSS 2021

In a \emph{data poisoning attack}, an attacker modifies, deletes, and/or inserts some training examples to corrupt the learnt machine learning model. \emph{Bootstrap Aggregating (bagging)} is a well-known ensemble learning method, which trains multiple base models on random subsamples of a training dataset using a base learning algorithm and uses majority vote to predict labels of testing examples. We prove the intrinsic certified robustness of bagging against data poisoning attacks. Specifically, we show that bagging with an arbitrary base learning algorithm provably predicts the same label for a testing example when the number of modified, deleted, and/or inserted training examples is bounded by a threshold. Moreover, we show that our derived threshold is tight if no assumptions on the base learning algorithm are made. We evaluate our method on MNIST and CIFAR10. For instance, our method achieves a certified accuracy of $91.1\%$ on MNIST when arbitrarily modifying, deleting, and/or inserting 100 training examples. Code is available at: \url{https://github.com/jjy1994/BaggingCertifyDataPoisoning}., Comment: Accepted by AAAI'21