Search

Robotic manipulation refers to the autonomous handling and interaction of robots with objects using advanced techniques in robotics and artificial intelligence. The advent of powerful tools such as large language models (LLMs) and large vision-language models (LVLMs) has significantly enhanced the capabilities of these robots in environmental perception and decision-making. However, the introduction of these intelligent agents has led to security threats such as jailbreak attacks and adversarial attacks. In this research, we take a further step by proposing a backdoor attack specifically targeting robotic manipulation and, for the first time, implementing backdoor attack in the physical world. By embedding a backdoor visual language model into the visual perception module within the robotic system, we successfully mislead the robotic arm's operation in the physical world, given the presence of common items as triggers. Experimental evaluations in the physical world demonstrate the effectiveness of the proposed backdoor attack., Comment: Initial version with preliminary results. We welcome any feedback or suggestions

Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional poisoning attacks are not as threatening as commonly believed. This is because they often cause differences in how the model performs on the training set compared to the validation set. Such inconsistency can alert defenders that their data has been poisoned, allowing them to take the necessary defensive actions. In this paper, we introduce a more threatening type of poisoning attack called the Deferred Poisoning Attack. This new attack allows the model to function normally during the training and validation phases but makes it very sensitive to evasion attacks or even natural noise. We achieve this by ensuring the poisoned model's loss function has a similar value as a normally trained model at each input sample but with a large local curvature. A similar model loss ensures that there is no obvious inconsistency between the training and validation accuracy, demonstrating high stealthiness. On the other hand, the large curvature implies that a small perturbation may cause a significant increase in model loss, leading to substantial performance degradation, which reflects a worse robustness. We fulfill this purpose by making the model have singular Hessian information at the optimal point via our proposed Singularization Regularization term. We have conducted both theoretical and empirical analyses of the proposed method and validated its effectiveness through experiments on image classification tasks. Furthermore, we have confirmed the hazards of this form of poisoning attack under more general scenarios using natural noise, offering a new perspective for research in the field of security.

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM., Comment: This paper has been accepted by the 38th Annual Conference on Neural Information Processing Systems (NeurIPS'24)

Embodied AI represents systems where AI is integrated into physical entities, enabling them to perceive and interact with their surroundings. Large Language Model (LLM), which exhibits powerful language understanding abilities, has been extensively employed in embodied AI by facilitating sophisticated task planning. However, a critical safety issue remains overlooked: could these embodied LLMs perpetrate harmful behaviors? In response, we introduce BadRobot, a novel attack paradigm aiming to make embodied LLMs violate safety and ethical constraints through typical voice-based user-system interactions. Specifically, three vulnerabilities are exploited to achieve this type of attack: (i) manipulation of LLMs within robotic systems, (ii) misalignment between linguistic outputs and physical actions, and (iii) unintentional hazardous behaviors caused by world knowledge's flaws. Furthermore, we construct a benchmark of various malicious physical action queries to evaluate BadRobot's attack performance. Based on this benchmark, extensive experiments against existing prominent embodied LLM frameworks (e.g., Voxposer, Code as Policies, and ProgPrompt) demonstrate the effectiveness of our BadRobot. Warning: This paper contains harmful AI-generated language and aggressive actions., Comment: 38 pages, 16 figures

Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victim models. Recently, some defense mechanisms have been proposed such as adversarial training, image transformation techniques, and image purification. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then begin by introducing Gaussian noise to absorb the poisons and then apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is available at https://github.com/CGCL-codes/ECLIPSE., Comment: Accepted by ESORICS 2024

Deep Learning (DL) powered by Deep Neural Networks (DNNs) has revolutionized various domains, yet understanding the intricacies of DNN decision-making and learning processes remains a significant challenge. Recent investigations have uncovered an interesting memorization phenomenon in which DNNs tend to memorize specific details from examples rather than learning general patterns, affecting model generalization, security, and privacy. This raises critical questions about the nature of generalization in DNNs and their susceptibility to security breaches. In this survey, we present a systematic framework to organize memorization definitions based on the generalization and security/privacy domains and summarize memorization evaluation methods at both the example and model levels. Through a comprehensive literature review, we explore DNN memorization behaviors and their impacts on security and privacy. We also introduce privacy vulnerabilities caused by memorization and the phenomenon of forgetting and explore its connection with memorization. Furthermore, we spotlight various applications leveraging memorization and forgetting mechanisms, including noisy label learning, privacy preservation, and model enhancement. This survey offers the first-in-kind understanding of memorization in DNNs, providing insights into its challenges and opportunities for enhancing AI development while addressing critical ethical concerns.

The Large Language Model (LLM) watermark is a newly emerging technique that shows promise in addressing concerns surrounding LLM copyright, monitoring AI-generated text, and preventing its misuse. The LLM watermark scheme commonly includes generating secret keys to partition the vocabulary into green and red lists, applying a perturbation to the logits of tokens in the green list to increase their sampling likelihood, thus facilitating watermark detection to identify AI-generated text if the proportion of green tokens exceeds a threshold. However, recent research indicates that watermarking methods using numerous keys are susceptible to removal attacks, such as token editing, synonym substitution, and paraphrasing, with robustness declining as the number of keys increases. Therefore, the state-of-the-art watermark schemes that employ fewer or single keys have been demonstrated to be more robust against text editing and paraphrasing. In this paper, we propose a novel green list stealing attack against the state-of-the-art LLM watermark scheme and systematically examine its vulnerability to this attack. We formalize the attack as a mixed integer programming problem with constraints. We evaluate our attack under a comprehensive threat model, including an extreme scenario where the attacker has no prior knowledge, lacks access to the watermark detector API, and possesses no information about the LLM's parameter settings or watermark injection/detection scheme. Extensive experiments on LLMs, such as OPT and LLaMA, demonstrate that our attack can successfully steal the green list and remove the watermark across all settings., Comment: 12 pages

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model training. This paper proposes a simple yet effective input-level backdoor detection (dubbed IBD-PSC) as a `firewall' to filter out malicious testing images. Our method is motivated by an intriguing phenomenon, i.e., parameter-oriented scaling consistency (PSC), where the prediction confidences of poisoned samples are significantly more consistent than those of benign ones when amplifying model parameters. In particular, we provide theoretical analysis to safeguard the foundations of the PSC phenomenon. We also design an adaptive method to select BN layers to scale up for effective detection. Extensive experiments are conducted on benchmark datasets, verifying the effectiveness and efficiency of our IBD-PSC method and its resistance to adaptive attacks. Codes are available at \href{https://github.com/THUYimingLi/BackdoorBox}{BackdoorBox}., Comment: Accepted to ICML 2024, 31 pages

Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context of real-world industrial scenarios, even the simplest defense suffices to defend against the state-of-the-art attack, 3DFed. A practical FL backdoor attack remains in a nascent stage of development. To bridge this gap, we present DarkFed. Initially, we emulate a series of fake clients, thereby achieving the attacker proportion typical of academic research scenarios. Given that these emulated fake clients lack genuine training data, we further propose a data-free approach to backdoor FL. Specifically, we delve into the feasibility of injecting a backdoor using a shadow dataset. Our exploration reveals that impressive attack performance can be achieved, even when there is a substantial gap between the shadow dataset and the main task dataset. This holds true even when employing synthetic data devoid of any semantic information as the shadow dataset. Subsequently, we strategically construct a series of covert backdoor updates in an optimized manner, mimicking the properties of benign updates, to evade detection by defenses. A substantial body of empirical evidence validates the tangible effectiveness of DarkFed., Comment: This paper has been accepted by IJCAI 2024

Recent advancements in machine learning and deep learning have brought algorithmic fairness into sharp focus, illuminating concerns over discriminatory decision making that negatively impacts certain individuals or groups. These concerns have manifested in legal, ethical, and societal challenges, including the erosion of trust in intelligent systems. In response, this survey delves into the existing literature on algorithmic fairness, specifically highlighting its multifaceted social consequences. We introduce a novel taxonomy based on 'tolerance', a term we define as the degree to which variations in fairness outcomes are acceptable, providing a structured approach to understanding the subtleties of fairness within algorithmic decisions. Our systematic review covers diverse industries, revealing critical insights into the balance between algorithmic decision making and social equity. By synthesizing these insights, we outline a series of emerging challenges and propose strategic directions for future research and policy making, with the goal of advancing the field towards more equitable algorithmic systems., Comment: 33 pages, 4 figures

Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: Sponge for triggering widespread misidentifications and Blinding for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement ($\sim$10\%-60\% absolute and $\sim$2-7$\times$ relative) in attack efficacy over state-of-the-art attacks., Comment: Accepted to IJCAI 2024

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Our extensive experiments, conducted across ten self-supervised training methods and six datasets, demonstrate that Gen-AF attains high testing accuracy and robust testing accuracy against state-of-the-art DAEs.

Model extraction attacks (MEAs) enable an attacker to replicate the functionality of a victim deep neural network (DNN) model by only querying its API service remotely, posing a severe threat to the security and integrity of pay-per-query DNN-based services. Although the majority of current research on MEAs has primarily concentrated on neural classifiers, there is a growing prevalence of image-to-image translation (I2IT) tasks in our everyday activities. However, techniques developed for MEA of DNN classifiers cannot be directly transferred to the case of I2IT, rendering the vulnerability of I2IT models to MEA attacks often underestimated. This paper unveils the threat of MEA in I2IT tasks from a new perspective. Diverging from the traditional approach of bridging the distribution gap between attacker queries and victim training samples, we opt to mitigate the effect caused by the different distributions, known as the domain shift. This is achieved by introducing a new regularization term that penalizes high-frequency noise, and seeking a flatter minimum to avoid overfitting to the shifted distribution. Extensive experiments on different image translation tasks, including image super-resolution and style transfer, are performed on different backbone victim models, and the new design consistently outperforms the baseline by a large margin across all metrics. A few real-life I2IT APIs are also verified to be extremely vulnerable to our attack, emphasizing the need for enhanced defenses and potentially revised API publishing policies., Comment: Accepted by AAAI 2024

Federated learning (FL) facilitates collaborative training of machine learning models among a large number of clients while safeguarding the privacy of their local datasets. However, FL remains susceptible to vulnerabilities such as privacy inference and inversion attacks. Single-server secure aggregation schemes were proposed to address these threats. Nonetheless, they encounter practical constraints due to their round and communication complexities. This work introduces Fluent, a round and communication-efficient secure aggregation scheme for private FL. Fluent has several improvements compared to state-of-the-art solutions like Bell et al. (CCS 2020) and Ma et al. (SP 2023): (1) it eliminates frequent handshakes and secret sharing operations by efficiently reusing the shares across multiple training iterations without leaking any private information; (2) it accomplishes both the consistency check and gradient unmasking in one logical step, thereby reducing another round of communication. With these innovations, Fluent achieves the fewest communication rounds (i.e., two in the collection phase) in the malicious server setting, in contrast to at least three rounds in existing schemes. This significantly minimizes the latency for geographically distributed clients; (3) Fluent also introduces Fluent-Dynamic with a participant selection algorithm and an alternative secret sharing scheme. This can facilitate dynamic client joining and enhance the system flexibility and scalability. We implemented Fluent and compared it with existing solutions. Experimental results show that Fluent improves the computational cost by at least 75% and communication overhead by at least 25% for normal clients. Fluent also reduces the communication overhead for the server at the expense of a marginal increase in computational cost.

Collaborative learning (CL) is a distributed learning framework that aims to protect user privacy by allowing users to jointly train a model by sharing their gradient updates only. However, gradient inversion attacks (GIAs), which recover users' training data from shared gradients, impose severe privacy threats to CL. Existing defense methods adopt different techniques, e.g., differential privacy, cryptography, and perturbation defenses, to defend against the GIAs. Nevertheless, all current defense methods suffer from a poor trade-off between privacy, utility, and efficiency. To mitigate the weaknesses of existing solutions, we propose a novel defense method, Dual Gradient Pruning (DGP), based on gradient pruning, which can improve communication efficiency while preserving the utility and privacy of CL. Specifically, DGP slightly changes gradient pruning with a stronger privacy guarantee. And DGP can also significantly improve communication efficiency with a theoretical analysis of its convergence and generalization. Our extensive experiments show that DGP can effectively defend against the most powerful GIAs and reduce the communication cost without sacrificing the model's utility.

\textit{Federated learning} (FL) and \textit{split learning} (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users' devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. \textit{Split federated learning} (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of robustness. In this paper, we present a novel poisoning attack known as MISA. It poisons both the top and bottom models, causing a \textbf{\underline{misa}}lignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention., Comment: This paper has been accepted by the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2024)

A backdoor attack in deep learning inserts a hidden backdoor in the model to trigger malicious behavior upon specific input patterns. Existing detection approaches assume a metric space (for either the original inputs or their latent representations) in which normal samples and malicious samples are separable. We show that this assumption has a severe limitation by introducing a novel SSDT (Source-Specific and Dynamic-Triggers) backdoor, which obscures the difference between normal samples and malicious samples. To overcome this limitation, we move beyond looking for a perfect metric space that would work for different deep-learning models, and instead resort to more robust topological constructs. We propose TED (Topological Evolution Dynamics) as a model-agnostic basis for robust backdoor detection. The main idea of TED is to view a deep-learning model as a dynamical system that evolves inputs to outputs. In such a dynamical system, a benign input follows a natural evolution trajectory similar to other benign inputs. In contrast, a malicious sample displays a distinct trajectory, since it starts close to benign samples but eventually shifts towards the neighborhood of attacker-specified target samples to activate the backdoor. Extensive evaluations are conducted on vision and natural language datasets across different network architectures. The results demonstrate that TED not only achieves a high detection rate, but also significantly outperforms existing state-of-the-art detection approaches, particularly in addressing the sophisticated SSDT attack. The code to reproduce the results is made public on GitHub., Comment: 18 pages. To appear in IEEE Symposium on Security and Privacy 2024

Unlearnable datasets lead to a drastic drop in the generalization performance of models trained on them by introducing elaborate and imperceptible perturbations into clean training sets. Many existing defenses, e.g., JPEG compression and adversarial training, effectively counter UDs based on norm-constrained additive noise. However, a fire-new type of convolution-based UDs have been proposed and render existing defenses all ineffective, presenting a greater challenge to defenders. To address this, we express the convolution-based unlearnable sample as the result of multiplying a matrix by a clean sample in a simplified scenario, and formalize the intra-class matrix inconsistency as $\Theta_{imi}$, inter-class matrix consistency as $\Theta_{imc}$ to investigate the working mechanism of the convolution-based UDs. We conjecture that increasing both of these metrics will mitigate the unlearnability effect. Through validation experiments that commendably support our hypothesis, we further design a random matrix to boost both $\Theta_{imi}$ and $\Theta_{imc}$, achieving a notable degree of defense effect. Hence, by building upon and extending these facts, we first propose a brand-new image COrruption that employs randomly multiplicative transformation via INterpolation operation to successfully defend against convolution-based UDs. Our approach leverages global pixel random interpolations, effectively suppressing the impact of multiplicative noise in convolution-based UDs. Additionally, we have also designed two new forms of convolution-based UDs, and find that our defense is the most effective against them.

The collaborative nature of federated learning (FL) poses a major threat in the form of manipulation of local training data and local updates, known as the Byzantine poisoning attack. To address this issue, many Byzantine-robust aggregation rules (AGRs) have been proposed to filter out or moderate suspicious local updates uploaded by Byzantine participants. This paper introduces a novel approach called AGRAMPLIFIER, aiming to simultaneously improve the robustness, fidelity, and efficiency of the existing AGRs. The core idea of AGRAMPLIFIER is to amplify the "morality" of local updates by identifying the most repressive features of each gradient update, which provides a clearer distinction between malicious and benign updates, consequently improving the detection effect. To achieve this objective, two approaches, namely AGRMP and AGRXAI, are proposed. AGRMP organizes local updates into patches and extracts the largest value from each patch, while AGRXAI leverages explainable AI methods to extract the gradient of the most activated features. By equipping AGRAMPLIFIER with the existing Byzantine-robust mechanisms, we successfully enhance the model's robustness, maintaining its fidelity and improving overall efficiency. AGRAMPLIFIER is universally compatible with the existing Byzantine-robust mechanisms. The paper demonstrates its effectiveness by integrating it with all mainstream AGR mechanisms. Extensive evaluations conducted on seven datasets from diverse domains against seven representative poisoning attacks consistently show enhancements in robustness, fidelity, and efficiency, with average gains of 40.08%, 39.18%, and 10.68%, respectively., Comment: Accepted by IEEE TIFS, this is the complete version

Graph-level anomaly detection (GLAD) aims to identify graphs that exhibit notable dissimilarity compared to the majority in a collection. However, current works primarily focus on evaluating graph-level abnormality while failing to provide meaningful explanations for the predictions, which largely limits their reliability and application scope. In this paper, we investigate a new challenging problem, explainable GLAD, where the learning objective is to predict the abnormality of each graph sample with corresponding explanations, i.e., the vital subgraph that leads to the predictions. To address this challenging problem, we propose a Self-Interpretable Graph aNomaly dETection model (SIGNET for short) that detects anomalous graphs as well as generates informative explanations simultaneously. Specifically, we first introduce the multi-view subgraph information bottleneck (MSIB) framework, serving as the design basis of our self-interpretable GLAD approach. This way SIGNET is able to not only measure the abnormality of each graph based on cross-view mutual information but also provide informative graph rationales by extracting bottleneck subgraphs from the input graph and its dual hypergraph in a self-supervised way. Extensive experiments on 16 datasets demonstrate the anomaly detection capability and self-interpretability of SIGNET., Comment: 23 pages; accepted to NeurIPS 2023

The intellectual property protection of deep learning (DL) models has attracted increasing serious concerns. Many works on intellectual property protection for Deep Neural Networks (DNN) models have been proposed. The vast majority of existing work uses DNN watermarking to verify the ownership of the model after piracy occurs, which is referred to as passive verification. On the contrary, we focus on a new type of intellectual property protection method named active copyright protection, which refers to active authorization control and user identity management of the DNN model. As of now, there is relatively limited research in the field of active DNN copyright protection. In this review, we attempt to clearly elaborate on the connotation, attributes, and requirements of active DNN copyright protection, provide evaluation methods and metrics for active copyright protection, review and analyze existing work on active DL model intellectual property protection, discuss potential attacks that active DL model copyright protection techniques may face, and provide challenges and future directions for active DL model intellectual property protection. This review is helpful to systematically introduce the new field of active DNN copyright protection and provide reference and foundation for subsequent work.

Federated Learning (FL) enables distributed participants (e.g., mobile devices) to train a global model without sharing data directly to a central server. Recent studies have revealed that FL is vulnerable to gradient inversion attack (GIA), which aims to reconstruct the original training samples and poses high risk against the privacy of clients in FL. However, most existing GIAs necessitate control over the server and rely on strong prior knowledge including batch normalization and data distribution information. In this work, we propose Client-side poisoning Gradient Inversion (CGI), which is a novel attack method that can be launched from clients. For the first time, we show the feasibility of a client-side adversary with limited knowledge being able to recover the training samples from the aggregated global model. We take a distinct approach in which the adversary utilizes a malicious model that amplifies the loss of a specific targeted class of interest. When honest clients employ the poisoned global model, the gradients of samples belonging to the targeted class are magnified, making them the dominant factor in the aggregated update. This enables the adversary to effectively reconstruct the private input belonging to other clients using the aggregated update. In addition, our CGI also features its ability to remain stealthy against Byzantine-robust aggregation rules (AGRs). By optimizing malicious updates and blending benign updates with a malicious replacement vector, our method remains undetected by these defense mechanisms. To evaluate the performance of CGI, we conduct experiments on various benchmark datasets, considering representative Byzantine-robust AGRs, and exploring diverse FL settings with different levels of adversary knowledge about the data. Our results demonstrate that CGI consistently and successfully extracts training input in all tested scenarios.

\textit{Federated learning} (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a \underline{\textbf{f}}our-\underline{\textbf{p}}ronged \underline{\textbf{d}}efense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is \textit{not independent and identically distributed} (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with $30\%$ improvement on model accuracy)., Comment: This paper has been accepted by the 31st ACM International Conference on Multimedia (MM '23)

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "large model". Despite this promising prospect, the security of pre-trained encoder has not been thoroughly investigated yet, especially when the pre-trained encoder is publicly available for commercial use. In this paper, we propose AdvEncoder, the first framework for generating downstream-agnostic universal adversarial examples based on the pre-trained encoder. AdvEncoder aims to construct a universal adversarial perturbation or patch for a set of natural images that can fool all the downstream tasks inheriting the victim pre-trained encoder. Unlike traditional adversarial example works, the pre-trained encoder only outputs feature vectors rather than classification labels. Therefore, we first exploit the high frequency component information of the image to guide the generation of adversarial examples. Then we design a generative attack framework to construct adversarial perturbations/patches by learning the distribution of the attack surrogate dataset to improve their attack success rates and transferability. Our results show that an attacker can successfully attack downstream tasks without knowing either the pre-training dataset or the downstream dataset. We also tailor four defenses for pre-trained encoders, the results of which further prove the attack ability of AdvEncoder., Comment: This paper has been accepted by the International Conference on Computer Vision (ICCV '23, October 2--6, 2023, Paris, France)

Adversarial examples (AEs) for DNNs have been shown to be transferable: AEs that successfully fool white-box surrogate models can also deceive other black-box models with different architectures. Although a bunch of empirical studies have provided guidance on generating highly transferable AEs, many of these findings lack explanations and even lead to inconsistent advice. In this paper, we take a further step towards understanding adversarial transferability, with a particular focus on surrogate aspects. Starting from the intriguing little robustness phenomenon, where models adversarially trained with mildly perturbed adversarial samples can serve as better surrogates, we attribute it to a trade-off between two predominant factors: model smoothness and gradient similarity. Our investigations focus on their joint effects, rather than their separate correlations with transferability. Through a series of theoretical and empirical analyses, we conjecture that the data distribution shift in adversarial training explains the degradation of gradient similarity. Building on these insights, we explore the impacts of data augmentation and gradient regularization on transferability and identify that the trade-off generally exists in the various training mechanisms, thus building a comprehensive blueprint for the regulation mechanism behind transferability. Finally, we provide a general route for constructing better surrogates to boost transferability which optimizes both model smoothness and gradient similarity simultaneously, e.g., the combination of input gradient regularization and sharpness-aware minimization (SAM), validated by extensive experiments. In summary, we call for attention to the united impacts of these two factors for launching effective transfer attacks, rather than optimizing one while ignoring the other, and emphasize the crucial role of manipulating surrogate models., Comment: IEEE Symposium on Security and Privacy (Oakland) 2024; Extended version of camera-ready

While collaborative systems provide convenience to our lives, they also face many security threats. One of them is the Low-rate Distributed Denial-of-Service (LDDoS) attack, which is a worthy concern. Unlike volumetric DDoS attacks that continuously send large volumes of traffic, LDDoS attacks are more stealthy and difficult to be detected owing to their low-volume feature. Due to its stealthiness and harmfulness, LDDoS has become one of the most destructive attacks in cloud computing. Although a few LDDoS attack detection and defense methods have been proposed, we observe that sophisticated LDDoS attacks (being more stealthy) can bypass some of the existing LDDoS defense methods. To verify our security observation, we proposed a new Feint-based LDDoS (F-LDDoS) attack strategy. In this strategy, we divide a Pulse Interval into a Feinting Interval and an Attack Interval. Unlike the previous LDDoS attacks, the bots also send traffic randomly in the Feinting Interval, thus disguise themselves as benign users during the F-LDDoS attack. In this way, although the victim detects that it is under an LDDoS attack, it is difficult to locate the attack sources and apply mitigation solutions. Experimental results show that F-LDDoS attack can degrade TCP bandwidth 6.7%-14% more than the baseline LDDoS attack. Besides, F-LDDoS also reduces the similarities between bot traffic and aggregated attack traffic, and increases the uncertainty of packet arrival. These results mean that the proposed F-LDDoS is more effective and more stealthy than normal LDDoS attacks. Finally, we discuss the countermeasures of F-LDDoS to draw the attention of defenders and improve the defense methods.

Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisoning attacks that optimize the amplitude of malicious perturbations along certain prescribed directions to cause DoS, we propose a Flexible Model Poisoning Attack (FMPA) that can achieve versatile attack goals. We consider a practical threat scenario where no extra knowledge about the FL system (e.g., aggregation rules or updates on benign devices) is available to adversaries. FMPA exploits the global historical information to construct an estimator that predicts the next round of the global model as a benign reference. It then fine-tunes the reference model to obtain the desired poisoned model with low accuracy and small perturbations. Besides the goal of causing DoS, FMPA can be naturally extended to launch a fine-grained controllable attack, making it possible to precisely reduce the global accuracy. Armed with precise control, malicious FL service providers can gain advantages over their competitors without getting noticed, hence opening a new attack surface in FL other than DoS. Even for the purpose of DoS, experiments show that FMPA significantly decreases the global accuracy, outperforming six state-of-the-art attacks., Comment: Accepted by IJCAI 2024

Adversarial attacks are a serious threat to the reliable deployment of machine learning models in safety-critical applications. They can misguide current models to predict incorrectly by slightly modifying the inputs. Recently, substantial work has shown that adversarial examples tend to deviate from the underlying data manifold of normal examples, whereas pre-trained masked language models can fit the manifold of normal NLP data. To explore how to use the masked language model in adversarial detection, we propose a novel textual adversarial example detection method, namely Masked Language Model-based Detection (MLMD), which can produce clearly distinguishable signals between normal examples and adversarial examples by exploring the changes in manifolds induced by the masked language model. MLMD features a plug and play usage (i.e., no need to retrain the victim model) for adversarial defense and it is agnostic to classification tasks, victim model's architectures, and to-be-defended attack methods. We evaluate MLMD on various benchmark textual datasets, widely studied machine learning models, and state-of-the-art (SOTA) adversarial attacks (in total $3*4*4 = 48$ settings). Experimental results show that MLMD can achieve strong performance, with detection accuracy up to 0.984, 0.967, and 0.901 on AG-NEWS, IMDB, and SST-2 datasets, respectively. Additionally, MLMD is superior, or at least comparable to, the SOTA detection defenses in detection accuracy and F1 score. Among many defenses based on the off-manifold assumption of adversarial examples, this work offers a new angle for capturing the manifold change. The code for this work is openly accessible at \url{https://github.com/mlmddetection/MLMDdetection}., Comment: 13 pages,3 figures

Point cloud completion, as the upstream procedure of 3D recognition and segmentation, has become an essential part of many tasks such as navigation and scene understanding. While various point cloud completion models have demonstrated their powerful capabilities, their robustness against adversarial attacks, which have been proven to be fatally malicious towards deep neural networks, remains unknown. In addition, existing attack approaches towards point cloud classifiers cannot be applied to the completion models due to different output forms and attack purposes. In order to evaluate the robustness of the completion models, we propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones, while being completed as another object with totally different semantic information. Specifically, we minimize the representation discrepancy between the adversarial example and the target point set to jointly explore the adversarial point clouds in the geometry space and the feature space. Furthermore, to launch a stealthier attack, we innovatively employ the neighbourhood density information to tailor the perturbation constraint, leading to geometry-aware and distribution-adaptive modifications for each point. Extensive experiments against different premier point cloud completion networks show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01. We conclude that existing completion models are severely vulnerable to adversarial examples, and state-of-the-art defenses for point cloud classification will be partially invalid when applied to incomplete and uneven point cloud data., Comment: Accepted by the 37th AAAI Conference on Artificial Intelligence (AAAI-23)

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where a backdoored model behaves normally with clean inputs but exhibits attacker-specified behaviors upon the inputs containing triggers. Most previous backdoor attacks mainly focus on either the all-to-one or all-to-all paradigm, allowing attackers to manipulate an input to attack a single target class. Besides, the two paradigms rely on a single trigger for backdoor activation, rendering attacks ineffective if the trigger is destroyed. In light of the above, we propose a new $M$-to-$N$ attack paradigm that allows an attacker to manipulate any input to attack $N$ target classes, and each backdoor of the $N$ target classes can be activated by any one of its $M$ triggers. Our attack selects $M$ clean images from each target class as triggers and leverages our proposed poisoned image generation framework to inject the triggers into clean images invisibly. By using triggers with the same distribution as clean training images, the targeted DNN models can generalize to the triggers during training, thereby enhancing the effectiveness of our attack on multiple target classes. Extensive experimental results demonstrate that our new backdoor attack is highly effective in attacking multiple target classes and robust against pre-processing operations and existing defenses., Comment: 14 pages; Accepted to IEEE Transactions on Circuits and Systems for Video Technology (2024)

Federated learning is a newly emerging distributed learning framework that facilitates the collaborative training of a shared global model among distributed participants with their privacy preserved. However, federated learning systems are vulnerable to Byzantine attacks from malicious participants, who can upload carefully crafted local model updates to degrade the quality of the global model and even leave a backdoor. While this problem has received significant attention recently, current defensive schemes heavily rely on various assumptions, such as a fixed Byzantine model, availability of participants' local data, minority attackers, IID data distribution, etc. To relax those constraints, this paper presents Robust-FL, the first prediction-based Byzantine-robust federated learning scheme where none of the assumptions is leveraged. The core idea of the Robust-FL is exploiting historical global model to construct an estimator based on which the local models will be filtered through similarity detection. We then cluster local models to adaptively adjust the acceptable differences between the local models and the estimator such that Byzantine users can be identified. Extensive experiments over different datasets show that our approach achieves the following advantages simultaneously: (i) independence of participants' local data, (ii) tolerance of majority attackers, (iii) generalization to variable Byzantine model., Comment: This paper has been accepted by the 18th International Conference on Mobility, Sensing and Networking (MSN 2022)

Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonstrated that deep neural networks (DNNs) are susceptible to adversarial examples, and exploring adversarial attack against deep hashing has attracted many research efforts. Nevertheless, backdoor attack, another famous threat to DNNs, has not been studied for deep hashing yet. Although various backdoor attacks have been proposed in the field of image classification, existing approaches failed to realize a truly imperceptive backdoor attack that enjoys invisible triggers and clean label setting simultaneously, and they also cannot meet the intrinsic demand of image retrieval backdoor. In this paper, we propose BadHash, the first generative-based imperceptible backdoor attack against deep hashing, which can effectively generate invisible and input-specific poisoned images with clean label. Specifically, we first propose a new conditional generative adversarial network (cGAN) pipeline to effectively generate poisoned samples. For any given benign image, it seeks to generate a natural-looking poisoned counterpart with a unique invisible trigger. In order to improve the attack effectiveness, we introduce a label-based contrastive learning network LabCLN to exploit the semantic characteristics of different labels, which are subsequently used for confusing and misleading the target model to learn the embedded trigger. We finally explore the mechanism of backdoor attacks on image retrieval in the hash space. Extensive experiments on multiple benchmark datasets verify that BadHash can generate imperceptible poisoned samples with strong attack ability and transferability over state-of-the-art deep hashing schemes., Comment: This paper has been accepted by the 30th ACM International Conference on Multimedia (MM '22, October 10--14, 2022, Lisboa, Portugal)

The usage of deep learning is being escalated in many applications. Due to its outstanding performance, it is being used in a variety of security and privacy-sensitive areas in addition to conventional applications. One of the key aspects of deep learning efficacy is to have abundant data. This trait leads to the usage of data which can be highly sensitive and private, which in turn causes wariness with regard to deep learning in the general public. Membership inference attacks are considered lethal as they can be used to figure out whether a piece of data belongs to the training dataset or not. This can be problematic with regards to leakage of training data information and its characteristics. To highlight the significance of these types of attacks, we propose an enhanced methodology for membership inference attacks based on adversarial robustness, by adjusting the directions of adversarial perturbations through label smoothing under a white-box setting. We evaluate our proposed method on three datasets: Fashion-MNIST, CIFAR-10, and CIFAR-100. Our experimental results reveal that the performance of our method surpasses that of the existing adversarial robustness-based method when attacking normally trained models. Additionally, through comparing our technique with the state-of-the-art metric-based membership inference methods, our proposed method also shows better performance when attacking adversarially trained models. The code for reproducing the results of this work is available at \url{https://github.com/plll4zzx/Evaluating-Membership-Inference-Through-Adversarial-Robustness}., Comment: Accepted by The Computer Journal. Pre-print version

Federated learning (FL) enables multiple clients to collaboratively train an accurate global model while protecting clients' data privacy. However, FL is susceptible to Byzantine attacks from malicious participants. Although the problem has gained significant attention, existing defenses have several flaws: the server irrationally chooses malicious clients for aggregation even after they have been detected in previous rounds; the defenses perform ineffectively against sybil attacks or in the heterogeneous data setting. To overcome these issues, we propose MAB-RFL, a new method for robust aggregation in FL. By modelling the client selection as an extended multi-armed bandit (MAB) problem, we propose an adaptive client selection strategy to choose honest clients that are more likely to contribute high-quality updates. We then propose two approaches to identify malicious updates from sybil and non-sybil attacks, based on which rewards for each client selection decision can be accurately evaluated to discourage malicious behaviors. MAB-RFL achieves a satisfying balance between exploration and exploitation on the potential benign clients. Extensive experimental results show that MAB-RFL outperforms existing defenses in three attack scenarios under different percentages of attackers., Comment: This paper has been published on the 31st International Joint Conference on Artificial Intelligence (IJCAI-22, Main Track, LONG Oral Presentation)

Machine learning promotes the continuous development of signal processing in various fields, including network traffic monitoring, EEG classification, face identification, and many more. However, massive user data collected for training deep learning models raises privacy concerns and increases the difficulty of manually adjusting the network structure. To address these issues, we propose a privacy-preserving neural architecture search (PP-NAS) framework based on secure multi-party computation to protect users' data and the model's parameters/hyper-parameters. PP-NAS outsources the NAS task to two non-colluding cloud servers for making full advantage of mixed protocols design. Complement to the existing PP machine learning frameworks, we redesign the secure ReLU and Max-pooling garbled circuits for significantly better efficiency ($3 \sim 436$ times speed-up). We develop a new alternative to approximate the Softmax function over secret shares, which bypasses the limitation of approximating exponential operations in Softmax while improving accuracy. Extensive analyses and experiments demonstrate PP-NAS's superiority in security, efficiency, and accuracy., Comment: Accepted by IEEE ISCC 2022

Fine-tuning attacks are effective in removing the embedded watermarks in deep learning models. However, when the source data is unavailable, it is challenging to just erase the watermark without jeopardizing the model performance. In this context, we introduce Attention Distraction (AD), a novel source data-free watermark removal attack, to make the model selectively forget the embedded watermarks by customizing continual learning. In particular, AD first anchors the model's attention on the main task using some unlabeled data. Then, through continual learning, a small number of \textit{lures} (randomly selected natural images) that are assigned a new label distract the model's attention away from the watermarks. Experimental results from different datasets and networks corroborate that AD can thoroughly remove the watermark with a small resource budget without compromising the model's performance on the main task, which outperforms the state-of-the-art works., Comment: Accepted by ICME2022

While deep face recognition (FR) systems have shown amazing performance in identification and verification, they also arouse privacy concerns for their excessive surveillance on users, especially for public face images widely spread on social networks. Recently, some studies adopt adversarial examples to protect photos from being identified by unauthorized face recognition systems. However, existing methods of generating adversarial face images suffer from many limitations, such as awkward visual, white-box setting, weak transferability, making them difficult to be applied to protect face privacy in reality. In this paper, we propose adversarial makeup transfer GAN (AMT-GAN), a novel face protection method aiming at constructing adversarial face images that preserve stronger black-box transferability and better visual quality simultaneously. AMT-GAN leverages generative adversarial networks (GAN) to synthesize adversarial face images with makeup transferred from reference images. In particular, we introduce a new regularization module along with a joint training strategy to reconcile the conflicts between the adversarial noises and the cycle consistence loss in makeup transfer, achieving a desirable balance between the attack strength and visual changes. Extensive experiments verify that compared with state of the arts, AMT-GAN can not only preserve a comfortable visual quality, but also achieve a higher attack success rate over commercial FR APIs, including Face++, Aliyun, and Microsoft., Comment: Accepted by CVPR2022. Code is available at https://github.com/CGCL-codes/AMT-GAN

Biometric authentication prospered because of its convenient use and security. Early generations of biometric mechanisms suffer from spoofing attacks. Recently, unobservable physiological signals (e.g., Electroencephalogram, Photoplethysmogram, Electrocardiogram) as biometrics offer a potential remedy to this problem. In particular, Photoplethysmogram (PPG) measures the change in blood flow of the human body by an optical method. Clinically, researchers commonly use PPG signals to obtain patients' blood oxygen saturation, heart rate, and other information to assist in diagnosing heart-related diseases. Since PPG signals contain a wealth of individual cardiac information, researchers have begun to explore their potential in cyber security applications. The unique advantages (simple acquisition, difficult to steal, and live detection) of the PPG signal allow it to improve the security and usability of the authentication in various aspects. However, the research on PPG-based authentication is still in its infancy. The lack of systematization hinders new research in this field. We conduct a comprehensive study of PPG-based authentication and discuss these applications' limitations before pointing out future research directions., Comment: Accepted by Computer & Security (COSE)

Advances of emerging Information and Communications Technology (ICT) technologies push the boundaries of what is possible and open up new markets for innovative ICT products and services. The adoption of ICT products and systems with security properties depends on consumers' confidence and markets' trust in the security functionalities and whether the assurance measures applied to these products meet the inherent security requirements. Such confidence and trust are primarily gained through the rigorous development of security requirements, validation criteria, evaluation, and certification. Common Criteria for Information Technology Security Evaluation (often referred to as Common Criteria or CC) is an international standard (ISO/IEC 15408) for cyber security certification. In this paper, we conduct a systematic review of the CC standards and its adoptions. Adoption barriers of the CC are also investigated based on the analysis of current trends in security evaluation. Specifically, we share the experiences and lessons gained through the recent Development of Australian Cyber Criteria Assessment (DACCA) project that promotes the CC among stakeholders in ICT security products related to specification, development, evaluation, certification and approval, procurement, and deployment. Best practices on developing Protection Profiles, recommendations, and future directions for trusted cybersecurity advancement are presented.

Recently emerged federated learning (FL) is an attractive distributed learning framework in which numerous wireless end-user devices can train a global model with the data remained autochthonous. Compared with the traditional machine learning framework that collects user data for centralized storage, which brings huge communication burden and concerns about data privacy, this approach can not only save the network bandwidth but also protect the data privacy. Despite the promising prospect, byzantine attack, an intractable threat in conventional distributed network, is discovered to be rather efficacious against FL as well. In this paper, we conduct a comprehensive investigation of the state-of-the-art strategies for defending against byzantine attacks in FL. We first provide a taxonomy for the existing defense solutions according to the techniques they used, followed by an across-the-board comparison and discussion. Then we propose a new byzantine attack method called weight attack to defeat those defense schemes, and conduct experiments to demonstrate its threat. The results show that existing defense solutions, although abundant, are still far from fully protecting FL. Finally, we indicate possible countermeasures for weight attack, and highlight several challenges and future research directions for mitigating byzantine attacks in FL., Comment: The paper has been accepted by the 21st IEEE International Conference on Trust, Security and Privacy in Computing and Communications (IEEE TrustCom-22)

Applying chaos theory for secure digital communications is promising and it is well acknowledged that in such applications the underlying chaotic systems should be carefully chosen. However, the requirements imposed on the chaotic systems are usually heuristic, without theoretic guarantee for the resultant communication scheme. Among all the primitives for secure communications, it is well-accepted that (pseudo) random numbers are most essential. Taking the well-studied two-dimensional coupled map lattice (2D CML) as an example, this paper performs a theoretical study towards pseudo-random number generation with the 2D CML. In so doing, an analytical expression of the Lyapunov exponent (LE) spectrum of the 2D CML is first derived. Using the LEs, one can configure system parameters to ensure the 2D CML only exhibits complex dynamic behavior, and then collect pseudo-random numbers from the system orbits. Moreover, based on the observation that least significant bit distributes more evenly in the (pseudo) random distribution, an extraction algorithm E is developed with the property that, when applied to the orbits of the 2D CML, it can squeeze uniform bits. In implementation, if fixed-point arithmetic is used in binary format with a precision of $z$ bits after the radix point, E can ensure that the deviation of the squeezed bits is bounded by $2^{-z}$ . Further simulation results demonstrate that the new method not only guide the 2D CML model to exhibit complex dynamic behavior, but also generate uniformly distributed independent bits. In particular, the squeezed pseudo random bits can pass both NIST 800-22 and TestU01 test suites in various settings. This study thereby provides a theoretical basis for effectively applying the 2D CML to secure communications., Comment: 10 pages, 11figures

The onerous media sharing task prompts resource-constrained media owners to seek help from a cloud platform, i.e., storing media contents in the cloud and letting the cloud do the sharing. There are three key security/privacy problems that need to be solved in the cloud media sharing scenario, including data privacy leakage and access control in the cloud, infringement on the owner's copyright, and infringement on the user's rights. In view of the fact that no single technique can solve the above three problems simultaneously, two cloud media sharing schemes are proposed in this paper, named FairCMS-I and FairCMS-II. By cleverly utilizing the proxy re-encryption technique and the asymmetric fingerprinting technique, FairCMS-I and FairCMS-II solve the above three problems with different privacy/efficiency trade-offs. Among them, FairCMS-I focuses more on cloud-side efficiency while FairCMS-II focuses more on the security of the media content, which provides owners with flexibility of choice. In addition, FairCMS-I and FairCMS-II also have advantages over existing cloud media sharing efforts in terms of optional IND-CPA (indistinguishability under chosen-plaintext attack) security and high cloud-side efficiency, as well as exemption from needing a trusted third party. Furthermore, FairCMS-I and FairCMS-II allow owners to reap significant local resource savings and thus can be seen as the privacy-preserving outsourcing of asymmetric fingerprinting. Finally, the feasibility and efficiency of FairCMS-I and FairCMS-II are demonstrated by experiments., Comment: Accepted by IEEE Transactions on Computational Social Systems

Deep learning models are known to be vulnerable to adversarial examples that are elaborately designed for malicious purposes and are imperceptible to the human perceptual system. Autoencoder, when trained solely over benign examples, has been widely used for (self-supervised) adversarial detection based on the assumption that adversarial examples yield larger reconstruction errors. However, because lacking adversarial examples in its training and the too strong generalization ability of autoencoder, this assumption does not always hold true in practice. To alleviate this problem, we explore how to detect adversarial examples with disentangled label/semantic features under the autoencoder structure. Specifically, we propose Disentangled Representation-based Reconstruction (DRR). In DRR, we train an autoencoder over both correctly paired label/semantic features and incorrectly paired label/semantic features to reconstruct benign and counterexamples. This mimics the behavior of adversarial examples and can reduce the unnecessary generalization ability of autoencoder. We compare our method with the state-of-the-art self-supervised detection methods under different adversarial attacks and different victim models, and it exhibits better performance in various metrics (area under the ROC curve, true positive rate, and true negative rate) for most attack settings. Though DRR is initially designed for visual tasks only, we demonstrate that it can be easily extended for natural language tasks as well. Notably, different from other autoencoder-based detectors, our method can provide resistance to the adaptive adversary., Comment: to appear in TrustCom 2022

The need for fast and strong image cryptosystems motivates researchers to develop new techniques to apply traditional cryptographic primitives in order to exploit the intrinsic features of digital images. One of the most popular and mature technique is the use of complex ynamic phenomena, including chaotic orbits and quantum walks, to generate the required key stream. In this paper, under the assumption of plaintext attacks we investigate the security of a classic diffusion mechanism (and of its variants) used as the core cryptographic rimitive in some image cryptosystems based on the aforementioned complex dynamic phenomena. We have theoretically found that regardless of the key schedule process, the data complexity for recovering each element of the equivalent secret key from these diffusion mechanisms is only O(1). The proposed analysis is validated by means of numerical examples. Some additional cryptographic applications of our work are also discussed., Comment: 16 pages, 7 figures