Search

Machine unlearning is new emerged technology that removes a subset of the training data from a trained model without affecting the model performance on the remaining data. This topic is becoming increasingly important in protecting user privacy and eliminating harmful or outdated data. The key challenge lies in effectively and efficiently unlearning specific information without compromising the model's utility on the retained data. For the pre-trained models, fine-tuning is an important way to achieve the unlearning target. Previous work typically fine-tuned the entire model's parameters, which incurs significant computation costs. In addition, the fine-tuning process may cause shifts in the intermediate layer features, affecting the model's overall utility. In this work, we propose a novel and efficient machine unlearning method on pre-trained models. We term the method as Residual Feature Alignment Unlearning. Specifically, we leverage LoRA (Low-Rank Adaptation) to decompose the model's intermediate features into pre-trained features and residual features. By adjusting the residual features, we align the unlearned model with the pre-trained model at the intermediate feature level to achieve both unlearning and remaining targets. The method aims to learn the zero residuals on the retained set and shifted residuals on the unlearning set. Extensive experiments on numerous datasets validate the effectiveness of our approach.

Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer vision, and more. Despite their powerful capabilities, pre-trained models have also sparked attention to the emerging security challenges associated with their real-world applications. Security and privacy issues, such as leaking privacy information and generating harmful responses, have seriously undermined users' confidence in these powerful models. Concerns are growing as model performance improves dramatically. Researchers are eager to explore the unique security and privacy issues that have emerged, their distinguishing factors, and how to defend against them. However, the current literature lacks a clear taxonomy of emerging attacks and defenses for pre-trained models, which hinders a high-level and comprehensive understanding of these questions. To fill the gap, we conduct a systematical survey on the security risks of pre-trained models, proposing a taxonomy of attack and defense methods based on the accessibility of pre-trained models' input and weights in various security test scenarios. This taxonomy categorizes attacks and defenses into No-Change, Input-Change, and Model-Change approaches. With the taxonomy analysis, we capture the unique security and privacy issues of pre-trained models, categorizing and summarizing existing security issues based on their characteristics. In addition, we offer a timely and comprehensive review of each category's strengths and limitations. Our survey concludes by highlighting potential new research opportunities in the security and privacy of pre-trained models.

In the rapid advancement of artificial intelligence, privacy protection has become crucial, giving rise to machine unlearning. Machine unlearning is a technique that removes specific data influences from trained models without the need for extensive retraining. However, it faces several key challenges, including accurately implementing unlearning, ensuring privacy protection during the unlearning process, and achieving effective unlearning without significantly compromising model performance. This paper presents a novel approach to machine unlearning by employing Layer-wise Relevance Analysis and Neuronal Path Perturbation. We address three primary challenges: the lack of detailed unlearning principles, privacy guarantees in zero-shot unlearning scenario, and the balance between unlearning effectiveness and model utility. Our method balances machine unlearning performance and model utility by identifying and perturbing highly relevant neurons, thereby achieving effective unlearning. By using data not present in the original training set during the unlearning process, we satisfy the zero-shot unlearning scenario and ensure robust privacy protection. Experimental results demonstrate that our approach effectively removes targeted data from the target unlearning model while maintaining the model's utility, offering a practical solution for privacy-preserving machine learning., Comment: 17 pages, 5 figures

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently learn and retain sensitive information and harmful content during training, raising significant ethical and legal concerns. To address these issues, machine unlearning has been introduced as a potential solution. While existing unlearning methods take into account the specific characteristics of LLMs, they often suffer from high computational demands, limited applicability, or the risk of catastrophic forgetting. To address these limitations, we propose a lightweight unlearning framework based on Retrieval-Augmented Generation (RAG) technology. By modifying the external knowledge base of RAG, we simulate the effects of forgetting without directly interacting with the unlearned LLM. We approach the construction of unlearned knowledge as a constrained optimization problem, deriving two key components that underpin the effectiveness of RAG-based unlearning. This RAG-based approach is particularly effective for closed-source LLMs, where existing unlearning methods often fail. We evaluate our framework through extensive experiments on both open-source and closed-source models, including ChatGPT, Gemini, Llama-2-7b-chat-hf, and PaLM 2. The results demonstrate that our approach meets five key unlearning criteria: effectiveness, universality, harmlessness, simplicity, and robustness. Meanwhile, this approach can extend to multimodal large language models and LLM-based agents., Comment: 15 pages, 9 figures, 9 tables

Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. While extensive research has focused on developing efficient unlearning strategies, the critical aspect of unlearning verification has been largely overlooked. Existing verification methods mainly rely on machine learning attack techniques, such as membership inference attacks (MIAs) or backdoor attacks. However, these methods, not being formally designed for verification purposes, exhibit limitations in robustness and only support a small, predefined subset of samples. Moreover, dependence on prepared sample-level modifications of MIAs or backdoor attacks restricts their applicability in Machine Learning as a Service (MLaaS) environments. To address these limitations, we propose a novel robustness verification scheme without any prior modifications, and can support verification on a much larger set. Our scheme employs an optimization-based method to recover the actual training samples from the model. By comparative analysis of recovered samples extracted pre- and post-unlearning, MLaaS users can verify the unlearning process. This verification scheme, operating exclusively through model parameters, avoids the need for any sample-level modifications prior to model training while supporting verification on a much larger set and maintaining robustness. The effectiveness of our proposed approach is demonstrated through theoretical analysis and experiments involving diverse models on various datasets in different scenarios.

Inspired by the rapid development of Large Language Models (LLMs), LLM agents have evolved to perform complex tasks. LLM agents are now extensively applied across various domains, handling vast amounts of data to interact with humans and execute tasks. The widespread applications of LLM agents demonstrate their significant commercial value; however, they also expose security and privacy vulnerabilities. At the current stage, comprehensive research on the security and privacy of LLM agents is highly needed. This survey aims to provide a comprehensive overview of the newly emerged privacy and security issues faced by LLM agents. We begin by introducing the fundamental knowledge of LLM agents, followed by a categorization and analysis of the threats. We then discuss the impacts of these threats on humans, environment, and other agents. Subsequently, we review existing defensive strategies, and finally explore future trends. Additionally, the survey incorporates diverse case studies to facilitate a more accessible understanding. By highlighting these critical security and privacy issues, the survey seeks to stimulate future research towards enhancing the security and privacy of LLM agents, thereby increasing their reliability and trustworthiness in future applications.

Model extraction attacks currently pose a non-negligible threat to the security and privacy of deep learning models. By querying the model with a small dataset and usingthe query results as the ground-truth labels, an adversary can steal a piracy model with performance comparable to the original model. Two key issues that cause the threat are, on the one hand, accurate and unlimited queries can be obtained by the adversary; on the other hand, the adversary can aggregate the query results to train the model step by step. The existing defenses usually employ model watermarking or fingerprinting to protect the ownership. However, these methods cannot proactively prevent the violation from happening. To mitigate the threat, we propose QUEEN (QUEry unlEarNing) that proactively launches counterattacks on potential model extraction attacks from the very beginning. To limit the potential threat, QUEEN has sensitivity measurement and outputs perturbation that prevents the adversary from training a piracy model with high performance. In sensitivity measurement, QUEEN measures the single query sensitivity by its distance from the center of its cluster in the feature space. To reduce the learning accuracy of attacks, for the highly sensitive query batch, QUEEN applies query unlearning, which is implemented by gradient reverse to perturb the softmax output such that the piracy model will generate reverse gradients to worsen its performance unconsciously. Experiments show that QUEEN outperforms the state-of-the-art defenses against various model extraction attacks with a relatively low cost to the model accuracy. The artifact is publicly available at https://anonymous.4open.science/r/queen implementation-5408/.

Graph data contains rich node features and unique edge information, which have been applied across various domains, such as citation networks or recommendation systems. Graph Neural Networks (GNNs) are specialized for handling such data and have shown impressive performance in many applications. However, GNNs may contain of sensitive information and susceptible to privacy attacks. For example, link stealing is a type of attack in which attackers infer whether two nodes are linked or not. Previous link stealing attacks primarily relied on posterior probabilities from the target GNN model, neglecting the significance of node features. Additionally, variations in node classes across different datasets lead to different dimensions of posterior probabilities. The handling of these varying data dimensions posed a challenge in using a single model to effectively conduct link stealing attacks on different datasets. To address these challenges, we introduce Large Language Models (LLMs) to perform link stealing attacks on GNNs. LLMs can effectively integrate textual features and exhibit strong generalizability, enabling attacks to handle diverse data dimensions across various datasets. We design two distinct LLM prompts to effectively combine textual features and posterior probabilities of graph nodes. Through these designed prompts, we fine-tune the LLM to adapt to the link stealing attack task. Furthermore, we fine-tune the LLM using multiple datasets and enable the LLM to learn features from different datasets simultaneously. Experimental results show that our approach significantly enhances the performance of existing link stealing attack tasks in both white-box and black-box scenarios. Our method can execute link stealing attacks across different datasets using only a single model, making link stealing attacks more applicable to real-world scenarios.

Federated learning is a promising privacy-preserving paradigm for distributed machine learning. In this context, there is sometimes a need for a specialized process called machine unlearning, which is required when the effect of some specific training samples needs to be removed from a learning model due to privacy, security, usability, and/or legislative factors. However, problems arise when current centralized unlearning methods are applied to existing federated learning, in which the server aims to remove all information about a class from the global model. Centralized unlearning usually focuses on simple models or is premised on the ability to access all training data at a central node. However, training data cannot be accessed on the server under the federated learning paradigm, conflicting with the requirements of the centralized unlearning process. Additionally, there are high computation and communication costs associated with accessing clients' data, especially in scenarios involving numerous clients or complex global models. To address these concerns, we propose a more effective and efficient federated unlearning scheme based on the concept of model explanation. Model explanation involves understanding deep networks and individual channel importance, so that this understanding can be used to determine which model channels are critical for classes that need to be unlearned. We select the most influential channels within an already-trained model for the data that need to be unlearned and fine-tune only influential channels to remove the contribution made by those data. In this way, we can simultaneously avoid huge consumption costs and ensure that the unlearned model maintains good performance. Experiments with different training models on various datasets demonstrate the effectiveness of the proposed approach., Comment: Accepted by IEEE Transactions on Big Data

Machine unlearning is an emerging technology that has come to attract widespread attention. A number of factors, including regulations and laws, privacy, and usability concerns, have resulted in this need to allow a trained model to forget some of its training data. Existing studies of machine unlearning mainly focus on unlearning requests that forget a cluster of instances or all instances from one class. While these approaches are effective in removing instances, they do not scale to scenarios where partial targets within an instance need to be forgotten. For example, one would like to only unlearn a person from all instances that simultaneously contain the person and other targets. Directly migrating instance-level unlearning to target-level unlearning will reduce the performance of the model after the unlearning process, or fail to erase information completely. To address these concerns, we have proposed a more effective and efficient unlearning scheme that focuses on removing partial targets from the model, which we name "target unlearning". Specifically, we first construct an essential graph data structure to describe the relationships between all important parameters that are selected based on the model explanation method. After that, we simultaneously filter parameters that are also important for the remaining targets and use the pruning-based unlearning method, which is a simple but effective solution to remove information about the target that needs to be forgotten. Experiments with different training models on various datasets demonstrate the effectiveness of the proposed approach.

Machine unlearning enables pre-trained models to eliminate the effects of partial training samples. Previous research has mainly focused on proposing efficient unlearning strategies. However, the verification of machine unlearning, or in other words, how to guarantee that a sample has been successfully unlearned, has been overlooked for a long time. Existing verification schemes typically rely on machine learning attack techniques, such as backdoor or membership inference attacks. As these techniques are not formally designed for verification, they are easily bypassed when an untrustworthy MLaaS undergoes rapid fine-tuning to merely meet the verification conditions, rather than executing real unlearning. In this paper, we propose a formal verification scheme, IndirectVerify, to determine whether unlearning requests have been successfully executed. We design influential sample pairs: one referred to as trigger samples and the other as reaction samples. Users send unlearning requests regarding trigger samples and use reaction samples to verify if the unlearning operation has been successfully carried out. We propose a perturbation-based scheme to generate those influential sample pairs. The objective is to perturb only a small fraction of trigger samples, leading to the reclassification of reaction samples. This indirect influence will be used for our verification purposes. In contrast to existing schemes that employ the same samples for all processes, our scheme, IndirectVerify, provides enhanced robustness, making it less susceptible to bypassing processes.

Machine unlearning enables pre-trained models to remove the effect of certain portions of training data. Previous machine unlearning schemes have mainly focused on unlearning a cluster of instances or all instances belonging to a specific class. These types of unlearning might have a significant impact on the model utility; and they may be inadequate for situations where we only need to unlearn features within instances, rather than the whole instances. Due to the different granularity, current unlearning methods can hardly achieve feature-level unlearning. To address the challenges of utility and granularity, we propose a refined granularity unlearning scheme referred to as ``feature unlearning". We first explore two distinct scenarios based on whether the annotation information about the features is given: feature unlearning with known annotations and feature unlearning without annotations. Regarding unlearning with known annotations, we propose an adversarial learning approach to automatically remove effects about features. For unlearning without annotations, we initially enable the output of one model's layer to identify different pattern features using model interpretability techniques. We proceed to filter features from instances based on these outputs with identifying ability. So that we can remove the feature impact based on filtered instances and the fine-tuning process. The effectiveness of our proposed approach is demonstrated through experiments involving diverse models on various datasets in different scenarios.

Federated learning is fast becoming a popular paradigm for applications involving mobile devices, banking systems, healthcare, and IoT systems. Hence, over the past five years, researchers have undertaken extensive studies on the privacy leaks, security threats, and fairness associated with these emerging models. For the most part, these three critical concepts have been studied in isolation; however, recent research has revealed that there may be an intricate interplay between them. For instance, some researchers have discovered that pursuing fairness may compromise privacy, or that efforts to enhance security can impact fairness. These emerging insights shed light on the fundamental connections between privacy, security, and fairness within federated learning, and, by delving deeper into these interconnections, we may be able to significantly augment research and development across the field. Consequently, the aim of this survey is to offer comprehensive descriptions of the privacy, security, and fairness issues in federated learning. Moreover, we analyze the complex relationships between these three dimensions of cyber safety and pinpoint the fundamental elements that influence each of them. We contend that there exists a trade-off between privacy and fairness and between security and gradient sharing. On this basis, fairness can function as a bridge between privacy and security to build models that are either more secure or more private. Building upon our observations, we identify the trade-offs between privacy and fairness and between security and fairness within the context of federated learning. The survey then concludes with promising directions for future research in this vanguard field.

Federated Learning (FL) is a distributed and privacy-preserving machine learning paradigm that coordinates multiple clients to train a model while keeping the raw data localized. However, this traditional FL poses some challenges, including privacy risks, data heterogeneity, communication bottlenecks, and system heterogeneity issues. To tackle these challenges, knowledge distillation (KD) has been widely applied in FL since 2020. KD is a validated and efficacious model compression and enhancement algorithm. The core concept of KD involves facilitating knowledge transfer between models by exchanging logits at intermediate or output layers. These properties make KD an excellent solution for the long-lasting challenges in FL. Up to now, there have been few reviews that summarize and analyze the current trend and methods for how KD can be applied in FL efficiently. This article aims to provide a comprehensive survey of KD-based FL, focusing on addressing the above challenges. First, we provide an overview of KD-based FL, including its motivation, basics, taxonomy, and a comparison with traditional FL and where KD should execute. We also analyze the critical factors in KD-based FL in the appendix, including teachers, knowledge, data, and methods. We discuss how KD can address the challenges in FL, including privacy protection, data heterogeneity, communication efficiency, and personalization. Finally, we discuss the challenges facing KD-based FL algorithms and future research directions. We hope this survey can provide insights and guidance for researchers and practitioners in the FL area.

With the rapid development of artificial intelligence, large language models (LLMs) have made remarkable advancements in natural language processing. These models are trained on vast datasets to exhibit powerful language understanding and generation capabilities across various applications, including machine translation, chatbots, and agents. However, LLMs have revealed a variety of privacy and security issues throughout their life cycle, drawing significant academic and industrial attention. Moreover, the risks faced by LLMs differ significantly from those encountered by traditional language models. Given that current surveys lack a clear taxonomy of unique threat models across diverse scenarios, we emphasize the unique privacy and security threats associated with five specific scenarios: pre-training, fine-tuning, retrieval-augmented generation systems, deployment, and LLM-based agents. Addressing the characteristics of each risk, this survey outlines potential threats and countermeasures. Research on attack and defense situations can offer feasible research directions, enabling more areas to benefit from LLMs.

The development of Large Language Models (LLMs) faces a significant challenge: the exhausting of publicly available fresh data. This is because training a LLM needs a large demanding of new data. Federated learning emerges as a promising solution, enabling collaborative model to contribute their private data to LLM global model. However, integrating federated learning with LLMs introduces new challenges, including the lack of transparency and the need for effective unlearning mechanisms. Transparency is essential to ensuring trust and fairness among participants, while accountability is crucial for deterring malicious behaviour and enabling corrective actions when necessary. To address these challenges, we propose a novel blockchain-based federated learning framework for LLMs that enhances transparency, accountability, and unlearning capabilities. Our framework leverages blockchain technology to create a tamper-proof record of each model's contributions and introduces an innovative unlearning function that seamlessly integrates with the federated learning mechanism. We investigate the impact of Low-Rank Adaptation (LoRA) hyperparameters on unlearning performance and integrate Hyperledger Fabric to ensure the security, transparency, and verifiability of the unlearning process. Through comprehensive experiments and analysis, we showcase the effectiveness of our proposed framework in achieving highly effective unlearning in LLMs trained using federated learning. Our findings highlight the feasibility of integrating blockchain technology into federated learning frameworks for LLMs., Comment: 16 pages, 7 figures

With the growing need to comply with privacy regulations and respond to user data deletion requests, integrating machine unlearning into IoT-based federated learning has become imperative. Traditional unlearning methods, however, often lack verifiable mechanisms, leading to challenges in establishing trust. This paper delves into the innovative integration of blockchain technology with federated learning to surmount these obstacles. Blockchain fortifies the unlearning process through its inherent qualities of immutability, transparency, and robust security. It facilitates verifiable certification, harmonizes security with privacy, and sustains system efficiency. We introduce a framework that melds blockchain with federated learning, thereby ensuring an immutable record of unlearning requests and actions. This strategy not only bolsters the trustworthiness and integrity of the federated learning model but also adeptly addresses efficiency and security challenges typical in IoT environments. Our key contributions encompass a certification mechanism for the unlearning process, the enhancement of data security and privacy, and the optimization of data management to ensure system responsiveness in IoT scenarios., Comment: 13 pages, 25 figures

In current AI era, users may request AI companies to delete their data from the training dataset due to the privacy concerns. As a model owner, retraining a model will consume significant computational resources. Therefore, machine unlearning is a new emerged technology to allow model owner to delete requested training data or a class with little affecting on the model performance. However, for large-scaling complex data, such as image or text data, unlearning a class from a model leads to a inferior performance due to the difficulty to identify the link between classes and model. An inaccurate class deleting may lead to over or under unlearning. In this paper, to accurately defining the unlearning class of complex data, we apply the definition of Concept, rather than an image feature or a token of text data, to represent the semantic information of unlearning class. This new representation can cut the link between the model and the class, leading to a complete erasing of the impact of a class. To analyze the impact of the concept of complex data, we adopt a Post-hoc Concept Bottleneck Model, and Integrated Gradients to precisely identify concepts across different classes. Next, we take advantage of data poisoning with random and targeted labels to propose unlearning methods. We test our methods on both image classification models and large language models (LLMs). The results consistently show that the proposed methods can accurately erase targeted information from models and can largely maintain the performance of the models.

Machine unlearning aims to enable models to forget specific data instances when receiving deletion requests. Current research centres on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts on the remaining data. Consequently, existing unlearning algorithms degrade the model's performance after unlearning, known as \textit{over-unlearning}. This paper addresses this critical yet under-explored issue by introducing machine \underline{U}nlearning via \underline{N}ull \underline{S}pace \underline{C}alibration (UNSC), which can accurately unlearn target samples without over-unlearning. On the contrary, by calibrating the decision space during unlearning, UNSC can significantly improve the model's performance on the remaining samples. In particular, our approach hinges on confining the unlearning process to a specified null space tailored to the remaining samples, which is augmented by strategically pseudo-labeling the unlearning samples. Comparative analyses against several established baselines affirm the superiority of our approach. Code is released at this \href{https://github.com/HQC-ML/Machine-Unlearning-via-Null-Space-Calibration}{URL}., Comment: Accepted by IJCAI-2024

Machine unlearning refers to the process of mitigating the influence of specific training data on machine learning models based on removal requests from data owners. However, one important area that has been largely overlooked in the research of unlearning is reinforcement learning. Reinforcement learning focuses on training an agent to make optimal decisions within an environment to maximize its cumulative rewards. During the training, the agent tends to memorize the features of the environment, which raises a significant concern about privacy. As per data protection regulations, the owner of the environment holds the right to revoke access to the agent's training data, thus necessitating the development of a novel and pressing research field, known as \emph{reinforcement unlearning}. Reinforcement unlearning focuses on revoking entire environments rather than individual data samples. This unique characteristic presents three distinct challenges: 1) how to propose unlearning schemes for environments; 2) how to avoid degrading the agent's performance in remaining environments; and 3) how to evaluate the effectiveness of unlearning. To tackle these challenges, we propose two reinforcement unlearning methods. The first method is based on decremental reinforcement learning, which aims to erase the agent's previously acquired knowledge gradually. The second method leverages environment poisoning attacks, which encourage the agent to learn new, albeit incorrect, knowledge to remove the unlearning environment. Particularly, to tackle the third challenge, we introduce the concept of ``environment inference attack'' to evaluate the unlearning outcomes., Comment: Accepted by NDSS 2025

Previous studies have developed fairness methods for biased models that exhibit discriminatory behaviors towards specific subgroups. While these models have shown promise in achieving fair predictions, recent research has identified their potential vulnerability to score-based membership inference attacks (MIAs). In these attacks, adversaries can infer whether a particular data sample was used during training by analyzing the model's prediction scores. However, our investigations reveal that these score-based MIAs are ineffective when targeting fairness-enhanced models in binary classifications. The attack models trained to launch the MIAs degrade into simplistic threshold models, resulting in lower attack performance. Meanwhile, we observe that fairness methods often lead to prediction performance degradation for the majority subgroups of the training data. This raises the barrier to successful attacks and widens the prediction gaps between member and non-member data. Building upon these insights, we propose an efficient MIA method against fairness-enhanced models based on fairness discrepancy results (FD-MIA). It leverages the difference in the predictions from both the original and fairness-enhanced models and exploits the observed prediction gaps as attack clues. We also explore potential strategies for mitigating privacy leakages. Extensive experiments validate our findings and demonstrate the efficacy of the proposed method., Comment: Accepted by IJCAI 2024

As machine learning continues to develop, and data misuse scandals become more prevalent, individuals are becoming increasingly concerned about their personal information and are advocating for the right to remove their data. Machine unlearning has emerged as a solution to erase training data from trained machine learning models. Despite its success in classifiers, research on Generative Adversarial Networks (GANs) is limited due to their unique architecture, including a generator and a discriminator. One challenge pertains to generator unlearning, as the process could potentially disrupt the continuity and completeness of the latent space. This disruption might consequently diminish the model's effectiveness after unlearning. Another challenge is how to define a criterion that the discriminator should perform for the unlearning images. In this paper, we introduce a substitution mechanism and define a fake label to effectively mitigate these challenges. Based on the substitution mechanism and fake label, we propose a cascaded unlearning approach for both item and class unlearning within GAN models, in which the unlearning and learning processes run in a cascaded manner. We conducted a comprehensive evaluation of the cascaded unlearning technique using the MNIST and CIFAR-10 datasets. Experimental results demonstrate that this approach achieves significantly improved item and class unlearning efficiency, reducing the required time by up to 185x and 284x for the MNIST and CIFAR-10 datasets, respectively, in comparison to retraining from scratch. Notably, although the model's performance experiences minor degradation after unlearning, this reduction is negligible when dealing with a minimal number of images (e.g., 64) and has no adverse effects on downstream tasks such as classification.

Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques. While spectrograms have demonstrated their capability for anti-spoofing, complementary information presented in multi-order spectral patterns have not been well explored, which limits their effectiveness for varying spoofing attacks. Therefore, we propose a novel deep learning method with a spectral fusion-reconstruction strategy, namely S2pecNet, to utilise multi-order spectral patterns for robust audio anti-spoofing representations. Specifically, spectral patterns up to second-order are fused in a coarse-to-fine manner and two branches are designed for the fine-level fusion from the spectral and temporal contexts. A reconstruction from the fused representation to the input spectrograms further reduces the potential fused information loss. Our method achieved the state-of-the-art performance with an EER of 0.77% on a widely used dataset: ASVspoof2019 LA Challenge.

Federated learning (FL) has been a hot topic in recent years. Ever since it was introduced, researchers have endeavored to devise FL systems that protect privacy or ensure fair results, with most research focusing on one or the other. As two crucial ethical notions, the interactions between privacy and fairness are comparatively less studied. However, since privacy and fairness compete, considering each in isolation will inevitably come at the cost of the other. To provide a broad view of these two critical topics, we presented a detailed literature review of privacy and fairness issues, highlighting unique challenges posed by FL and solutions in federated settings. We further systematically surveyed different interactions between privacy and fairness, trying to reveal how privacy and fairness could affect each other and point out new research directions in fair and private FL.

Model inversion attacks involve reconstructing the training data of a target model, which raises serious privacy concerns for machine learning models. However, these attacks, especially learning-based methods, are likely to suffer from low attack accuracy, i.e., low classification accuracy of these reconstructed data by machine learning classifiers. Recent studies showed an alternative strategy of model inversion attacks, GAN-based optimization, can improve the attack accuracy effectively. However, these series of GAN-based attacks reconstruct only class-representative training data for a class, whereas learning-based attacks can reconstruct diverse data for different training data in each class. Hence, in this paper, we propose a new training paradigm for a learning-based model inversion attack that can achieve higher attack accuracy in a black-box setting. First, we regularize the training process of the attack model with an added semantic loss function and, second, we inject adversarial examples into the training data to increase the diversity of the class-related parts (i.e., the essential features for classification tasks) in training data. This scheme guides the attack model to pay more attention to the class-related parts of the original data during the data reconstruction process. The experimental results show that our method greatly boosts the performance of existing learning-based model inversion attacks. Even when no extra queries to the target model are allowed, the approach can still improve the attack accuracy of reconstructed data. This new attack shows that the severity of the threat from learning-based model inversion adversaries is underestimated and more robust defenses are required., Comment: 18 pages, 13 figures

Machine learning has attracted widespread attention and evolved into an enabling technology for a wide range of highly successful applications, such as intelligent computer vision, speech recognition, medical diagnosis, and more. Yet a special need has arisen where, due to privacy, usability, and/or the right to be forgotten, information about some specific samples needs to be removed from a model, called machine unlearning. This emerging technology has drawn significant interest from both academics and industry due to its innovation and practicality. At the same time, this ambitious problem has led to numerous research efforts aimed at confronting its challenges. To the best of our knowledge, no study has analyzed this complex topic or compared the feasibility of existing unlearning solutions in different kinds of scenarios. Accordingly, with this survey, we aim to capture the key concepts of unlearning techniques. The existing solutions are classified and summarized based on their characteristics within an up-to-date and comprehensive review of each category's advantages and limitations. The survey concludes by highlighting some of the outstanding issues with unlearning techniques, along with some feasible directions for new research opportunities.

GAN-generated image detection now becomes the first line of defense against the malicious uses of machine-synthesized image manipulations such as deepfakes. Although some existing detectors work well in detecting clean, known GAN samples, their success is largely attributable to overfitting unstable features such as frequency artifacts, which will cause failures when facing unknown GANs or perturbation attacks. To overcome the issue, we propose a robust detection framework based on a novel multi-view image completion representation. The framework first learns various view-to-image tasks to model the diverse distributions of genuine images. Frequency-irrelevant features can be represented from the distributional discrepancies characterized by the completion models, which are stable, generalized, and robust for detecting unknown fake patterns. Then, a multi-view classification is devised with elaborated intra- and inter-view learning strategies to enhance view-specific feature representation and cross-view feature aggregation, respectively. We evaluated the generalization ability of our framework across six popular GANs at different resolutions and its robustness against a broad range of perturbation attacks. The results confirm our method's improved effectiveness, generalization, and robustness over various baselines., Comment: Accepted to IJCAI 2023

Image deep steganography (IDS) is a technique that utilizes deep learning to embed a secret image invisibly into a cover image to generate a container image. However, the container images generated by convolutional neural networks (CNNs) are vulnerable to attacks that distort their high-frequency components. To address this problem, we propose a novel method called Low-frequency Image Deep Steganography (LIDS) that allows frequency distribution manipulation in the embedding process. LIDS extracts a feature map from the secret image and adds it to the cover image to yield the container image. The container image is not directly output by the CNNs, and thus, it does not contain high-frequency artifacts. The extracted feature map is regulated by a frequency loss to ensure that its frequency distribution mainly concentrates on the low-frequency domain. To further enhance robustness, an attack layer is inserted to damage the container image. The retrieval network then retrieves a recovered secret image from a damaged container image. Our experiments demonstrate that LIDS outperforms state-of-the-art methods in terms of robustness, while maintaining high fidelity and specificity. By avoiding high-frequency artifacts and manipulating the frequency distribution of the embedded feature map, LIDS achieves improved robustness against attacks that distort the high-frequency components of container images.

In recent years, there has been significant advancement in the field of model watermarking techniques. However, the protection of image-processing neural networks remains a challenge, with only a limited number of methods being developed. The objective of these techniques is to embed a watermark in the output images of the target generative network, so that the watermark signal can be detected in the output of a surrogate model obtained through model extraction attacks. This promising technique, however, has certain limits. Analysis of the frequency domain reveals that the watermark signal is mainly concealed in the high-frequency components of the output. Thus, we propose an overwriting attack that involves forging another watermark in the output of the generative network. The experimental results demonstrate the efficacy of this attack in sabotaging existing watermarking schemes for image-processing networks, with an almost 100% success rate. To counter this attack, we devise an adversarial framework for the watermarking network. The framework incorporates a specially designed adversarial training step, where the watermarking network is trained to defend against the overwriting network, thereby enhancing its robustness. Additionally, we observe an overfitting phenomenon in the existing watermarking method, which can render it ineffective. To address this issue, we modify the training process to eliminate the overfitting problem.

Reinforcement learning (RL) is one of the most important branches of AI. Due to its capacity for self-adaption and decision-making in dynamic environments, reinforcement learning has been widely applied in multiple areas, such as healthcare, data markets, autonomous driving, and robotics. However, some of these applications and systems have been shown to be vulnerable to security or privacy attacks, resulting in unreliable or unstable services. A large number of studies have focused on these security and privacy problems in reinforcement learning. However, few surveys have provided a systematic review and comparison of existing problems and state-of-the-art solutions to keep up with the pace of emerging threats. Accordingly, we herein present such a comprehensive review to explain and summarize the challenges associated with security and privacy in reinforcement learning from a new perspective, namely that of the Markov Decision Process (MDP). In this survey, we first introduce the key concepts related to this area. Next, we cover the security and privacy issues linked to the state, action, environment, and reward function of the MDP process, respectively. We further highlight the special characteristics of security and privacy methodologies related to reinforcement learning. Finally, we discuss the possible future research directions within this area.

As a booming research area in the past decade, deep learning technologies have been driven by big data collected and processed on an unprecedented scale. However, privacy concerns arise due to the potential leakage of sensitive information from the training data. Recent research has revealed that deep learning models are vulnerable to various privacy attacks, including membership inference attacks, attribute inference attacks, and gradient inversion attacks. Notably, the efficacy of these attacks varies from model to model. In this paper, we answer a fundamental question: Does model architecture affect model privacy? By investigating representative model architectures from convolutional neural networks (CNNs) to Transformers, we demonstrate that Transformers generally exhibit higher vulnerability to privacy attacks than CNNs. Additionally, we identify the micro design of activation layers, stem layers, and LN layers, as major factors contributing to the resilience of CNNs against privacy attacks, while the presence of attention modules is another main factor that exacerbates the privacy vulnerability of Transformers. Our discovery reveals valuable insights for deep learning models to defend against privacy attacks and inspires the research community to develop privacy-friendly model architectures., Comment: To appear in USENIX Security 2024

Nowadays, the development of information technology is growing rapidly. In the big data era, the privacy of personal information has been more pronounced. The major challenge is to find a way to guarantee that sensitive personal information is not disclosed while data is published and analyzed. Centralized differential privacy is established on the assumption of a trusted third-party data curator. However, this assumption is not always true in reality. As a new privacy preservation model, local differential privacy has relatively strong privacy guarantees. Although federated learning has relatively been a privacy-preserving approach for distributed learning, it still introduces various privacy concerns. To avoid privacy threats and reduce communication costs, in this article, we propose integrating federated learning and local differential privacy with momentum gradient descent to improve the performance of machine learning models., Comment: There is a crucial definition error of local differential privacy

DeepFakes are raising significant social concerns. Although various DeepFake detectors have been developed as forensic countermeasures, these detectors are still vulnerable to attacks. Recently, a few attacks, principally adversarial attacks, have succeeded in cloaking DeepFake images to evade detection. However, these attacks have typical detector-specific designs, which require prior knowledge about the detector, leading to poor transferability. Moreover, these attacks only consider simple security scenarios. Less is known about how effective they are in high-level scenarios where either the detectors or the attacker's knowledge varies. In this paper, we solve the above challenges with presenting a novel detector-agnostic trace removal attack for DeepFake anti-forensics. Instead of investigating the detector side, our attack looks into the original DeepFake creation pipeline, attempting to remove all detectable natural DeepFake traces to render the fake images more "authentic". To implement this attack, first, we perform a DeepFake trace discovery, identifying three discernible traces. Then a trace removal network (TR-Net) is proposed based on an adversarial learning framework involving one generator and multiple discriminators. Each discriminator is responsible for one individual trace representation to avoid cross-trace interference. These discriminators are arranged in parallel, which prompts the generator to remove various traces simultaneously. To evaluate the attack efficacy, we crafted heterogeneous security scenarios where the detectors were embedded with different levels of defense and the attackers' background knowledge of data varies. The experimental results show that the proposed attack can significantly compromise the detection accuracy of six state-of-the-art DeepFake detectors while causing only a negligible loss in visual quality to the original DeepFake samples.

Machine learning models are vulnerable to data inference attacks, such as membership inference and model inversion attacks. In these types of breaches, an adversary attempts to infer a data record's membership in a dataset or even reconstruct this data record using a confidence score vector predicted by the target model. However, most existing defense methods only protect against membership inference attacks. Methods that can combat both types of attacks require a new model to be trained, which may not be time-efficient. In this paper, we propose a differentially private defense method that handles both types of attacks in a time-efficient manner by tuning only one parameter, the privacy budget. The central idea is to modify and normalize the confidence score vectors with a differential privacy mechanism which preserves privacy and obscures membership and reconstructed data. Moreover, this method can guarantee the order of scores in the vector to avoid any loss in classification accuracy. The experimental results show the method to be an effective and timely defense against both membership inference and model inversion attacks with no reduction in accuracy.

Transfer learning is an important approach that produces pre-trained teacher models which can be used to quickly build specialized student models. However, recent research on transfer learning has found that it is vulnerable to various attacks, e.g., misclassification and backdoor attacks. However, it is still not clear whether transfer learning is vulnerable to model inversion attacks. Launching a model inversion attack against transfer learning scheme is challenging. Not only does the student model hide its structural parameters, but it is also inaccessible to the adversary. Hence, when targeting a student model, both the white-box and black-box versions of existing model inversion attacks fail. White-box attacks fail as they need the target model's parameters. Black-box attacks fail as they depend on making repeated queries of the target model. However, they may not mean that transfer learning models are impervious to model inversion attacks. Hence, with this paper, we initiate research into model inversion attacks against transfer learning schemes with two novel attack methods. Both are black-box attacks, suiting different situations, that do not rely on queries to the target student model. In the first method, the adversary has the data samples that share the same distribution as the training set of the teacher model. In the second method, the adversary does not have any such samples. Experiments show that highly recognizable data records can be recovered with both of these methods. This means that even if a model is an inaccessible black-box, it can still be inverted.

In a model inversion attack, an adversary attempts to reconstruct the data records, used to train a target model, using only the model's output. In launching a contemporary model inversion attack, the strategies discussed are generally based on either predicted confidence score vectors, i.e., black-box attacks, or the parameters of a target model, i.e., white-box attacks. However, in the real world, model owners usually only give out the predicted labels; the confidence score vectors and model parameters are hidden as a defense mechanism to prevent such attacks. Unfortunately, we have found a model inversion method that can reconstruct the input data records based only on the output labels. We believe this is the attack that requires the least information to succeed and, therefore, has the best applicability. The key idea is to exploit the error rate of the target model to compute the median distance from a set of data records to the decision boundary of the target model. The distance, then, is used to generate confidence score vectors which are adopted to train an attack model to reconstruct the data records. The experimental results show that highly recognizable data records can be reconstructed with far less information than existing methods.

Deep generative models have gained much attention given their ability to generate data for applications as varied as healthcare to financial technology to surveillance, and many more - the most popular models being generative adversarial networks and variational auto-encoders. Yet, as with all machine learning models, ever is the concern over security breaches and privacy leaks and deep generative models are no exception. These models have advanced so rapidly in recent years that work on their security is still in its infancy. In an attempt to audit the current and future threats against these models, and to provide a roadmap for defense preparations in the short term, we prepared this comprehensive and specialized survey on the security and privacy preservation of GANs and VAEs. Our focus is on the inner connection between attacks and model architectures and, more specifically, on five components of deep generative models: the training data, the latent code, the generators/decoders of GANs/ VAEs, the discriminators/encoders of GANs/ VAEs, and the generated data. For each model, component and attack, we review the current research progress and identify the key challenges. The paper concludes with a discussion of possible future attacks and research directions in the field., Comment: To be published in IEEE Transactions on Knowledge and Data Engineering