Recent advancements in Large Vision-Language Models (LVLMs) have shown groundbreaking capabilities across diverse multimodal tasks. However, these models remain vulnerable to adversarial jailbreak attacks, where adversaries craft subtle perturbations to bypass safety mechanisms and trigger harmful outputs. Existing white-box attacks methods require full model accessibility, suffer from computing costs and exhibit insufficient adversarial transferability, making them impractical for real-world, black-box settings. To address these limitations, we propose a black-box jailbreak attack on LVLMs via Zeroth-Order optimization using Simultaneous Perturbation Stochastic Approximation (ZO-SPSA). ZO-SPSA provides three key advantages: (i) gradient-free approximation by input-output interactions without requiring model knowledge, (ii) model-agnostic optimization without the surrogate model and (iii) lower resource requirements with reduced GPU memory consumption. We evaluate ZO-SPSA on three LVLMs, including InstructBLIP, LLaVA and MiniGPT-4, achieving the highest jailbreak success rate of 83.0% on InstructBLIP, while maintaining imperceptible perturbations comparable to white-box methods. Moreover, adversarial examples generated from MiniGPT-4 exhibit strong transferability to other LVLMs, with ASR reaching 64.18%. These findings underscore the real-world feasibility of black-box jailbreaks and expose critical weaknesses in the safety mechanisms of current LVLMs
Frequency spectrum has played a significant role in learning unique and discriminating features for object recognition. Both low and high frequency information present in images have been extracted and learnt by a host of representation learning techniques, including deep learning. Inspired by this observation, we introduce a novel class of adversarial attacks, namely `WaveTransform', that creates adversarial noise corresponding to low-frequency and high-frequency subbands, separately (or in combination). The frequency subbands are analyzed using wavelet decomposition; the subbands are corrupt…
The Pennsylvania State University（宾夕法尼亚州立大学）；United States Army Research Laboratory（美国陆军研究实验室）
Machine learning models are frequently used to solve complex security problems, as well as to make decisions in sensitive situations like guiding autonomous vehicles or predicting financial market behaviors. Previous efforts have shown that numerous machine learning models were vulnerable to adversarial manipulations of their inputs taking the form of adversarial samples. Such inputs are crafted by adding carefully selected perturbations to legitimate inputs so as to force the machine learning model to misbehave, for instance by outputting a wrong class if the machine learning task of interest…
In manufacturing, unexpected failures are considered a primary operational risk, as they can hinder productivity and can incur huge losses. State-of-the-art Prognostics and Health Management (PHM) systems incorporate Deep Learning (DL) algorithms and Internet of Things (IoT) devices to ascertain the health status of equipment, and thus reduce the downtime, maintenance cost and increase the productivity. Unfortunately, IoT sensors and DL algorithms, both are vulnerable to cyber attacks, and hence pose a significant threat to PHM systems. In this paper, we adopt the adversarial example crafting …
Computational paralinguistic analysis is increasingly being used in a wide range of cyber applications, including security-sensitive applications such as speaker verification, deceptive speech detection, and medical diagnostics. While state-of-the-art machine learning techniques, such as deep neural networks, can provide robust and accurate speech analysis, they are susceptible to adversarial attacks. In this work, we propose an end-to-end scheme to generate adversarial examples for computational paralinguistic applications by perturbing directly the raw waveform of an audio recording rather t…
The surge in the internet of things (IoT) devices seriously threatens the current IoT security landscape, which requires a robust network intrusion detection system (NIDS). Despite superior detection accuracy, existing machine learning or deep learning based NIDS are vulnerable to adversarial examples. Recently, generative adversarial networks (GANs) have become a prevailing method in adversarial examples crafting. However, the nature of discrete network traffic at the packet level makes it hard for GAN to craft adversarial traffic as GAN is efficient in generating continuous data like image s…
University of New South Wales（新南威尔士大学）；University of Technology Sydney（悉尼科技大学）；University of Adelaide（阿德莱德大学）
Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial examples to show their diverse distributions and then augment recommendation systems by detecting potential attacks with a deep learning-based classifier based on the crafted data. Finally, we study the attack strength and frequency of adversarial examples and evaluate our model on standard datasets with multiple crafting methods. Our extensive experiments show tha…
State of the art deep learning techniques are known to be vulnerable to evasion attacks where an adversarial sample is generated from a malign sample and misclassified as benign. Detection of encrypted malware command and control traffic based on TCP/IP flow features can be framed as a learning task and is thus vulnerable to evasion attacks. However, unlike e.g. in image processing where generated adversarial samples can be directly mapped to images, going from flow features to actual TCP/IP packets requires crafting the sequence of packets, with no established approach for such crafting and a…
Numerous methods for crafting adversarial examples were proposed recently with high success rate. Since most existing machine learning based classifiers normalize images into some continuous, real vector, domain firstly, attacks often craft adversarial examples in such domain. However, "adversarial" examples may become benign after denormalizing them back into the discrete integer domain, known as the discretization problem. This problem was mentioned in some work, but has received relatively little attention. In this work, we first conduct a comprehensive study of existing methods and tools f…
Over the past decade, side-channels have proven to be significant and practical threats to modern computing systems. Recent attacks have all exploited the underlying shared hardware. While practical, mounting such a complicated attack is still akin to listening on a private conversation in a crowded train station. The attacker has to either perform significant manual labor or use AI systems to automate the process. The recent academic literature points to the latter option. With the abundance of cheap computing power and the improvements made in AI, it is quite advantageous to automate such ta…
Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to adversarial example attack, which generates malicious output by adding slight perturbations to the input. Previous adversarial example crafting methods, however, use simple metrics to evaluate the distances between the original examples and the adversarial ones, which could be easily detected by human eyes. In addition, these attacks are often not robust due to the in…
CISPA（CISPA亥姆霍兹信息安全中心）；Saarland University（萨尔大学）；Pennsylvania State University（宾夕法尼亚州立大学）；MPI-SWS（马克斯·普朗克软件系统研究所）
Deep neural networks, like many other machine learning models, have recently been shown to lack robustness against adversarially crafted inputs. These inputs are derived from regular inputs by minor yet carefully selected perturbations that deceive machine learning models into desired misclassifications. Existing work in this emerging field was largely specific to the domain of image classification, since the high-entropy of images can be conveniently manipulated without changing the images' overall visual appearance. Yet, it remains unclear how such attacks translate to more security-sensitiv…
IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Tencent AI Lab（腾讯人工智能实验室）；University of California, Davis（加利福尼亚大学戴维斯分校）；The Cooper Union（库伯联盟）
Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples - a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to misclassify. Existing methods for crafting adversarial examples are based on $L_2$ and $L_\infty$ distortion metrics. However, despite the fact that $L_1$ distortion accounts for the total variation and encourages sparsity in the perturbation, little has been developed for crafting $L_1$-based adversarial examples. In this paper, we formulate the process of attacking DNNs via adversarial …
EPFL（洛桑联邦理工学院）；University College London（伦敦大学学院）；University of California, Berkeley（加州大学伯克利分校）
Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The existing literature on provable adversarial robustness of models, however, exclusively focuses on robustness to gradient-based attacks in domains such as images. These attacks model the adversarial cost, e.g., amount of distortion applied to an image, as a $p$-norm. We argue that this approach is not well-suited to model adversarial costs in constrained doma…
Recent work has shown how easily white-box adversarial attacks can be applied to state-of-the-art image classifiers. However, real-life scenarios resemble more the black-box adversarial conditions, lacking transparency and usually imposing natural, hard constraints on the query budget. We propose $\textbf{EvoBA}$, a black-box adversarial attack based on a surprisingly simple evolutionary search strategy. $\textbf{EvoBA}$ is query-efficient, minimizes $L_0$ adversarial perturbations, and does not require any form of training. $\textbf{EvoBA}$ shows efficiency and efficacy through results that a…
The Pennsylvania State University（宾夕法尼亚州立大学）；United States Army Combat Capabilities Development Command Army Research Laboratory（美国陆军作战能力发展司令部陆军研究实验室）
Machine learning is vulnerable to adversarial examples-inputs designed to cause models to perform poorly. However, it is unclear if adversarial examples represent realistic inputs in the modeled domains. Diverse domains such as networks and phishing have domain constraints-complex relationships between features that an adversary must satisfy for an attack to be realized (in addition to any adversary-specific goals). In this paper, we explore how domain constraints limit adversarial capabilities and how adversaries can adapt their strategies to create realistic (constraint-compliant) examples. …
Beijing Institute of Technology（北京理工大学）；Beijing Institute of Technology Chongqing Innovation Center（北京理工大学重庆创新中心）
Deep neural networks (DNNs) have achieved remarkable success in diverse fields. However, it has been demonstrated that DNNs are very vulnerable to adversarial examples even in black-box settings. A large number of black-box attack methods have been proposed to in the literature. However, those methods usually suffer from low success rates and large query counts, which cannot fully satisfy practical purposes. In this paper, we propose a hybrid attack method which trains meta adversarial perturbations (MAPs) on surrogate models and performs black-box attacks by estimating gradients of the models…
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland, College Park（马里兰大学帕克分校）
The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same constraints. In this work, we show that different attack algorithms produce adversarial examples which are distinct not only in their effectiveness but also in how they qualitatively affect their victims. We begin by demonstrating that one can determine the attack algorithm that crafted an adversarial example. Then, we leverage recent advances in parameter-space salie…
North Carolina State University（北卡罗来纳州立大学）；ETH Zürich（苏黎世联邦理工学院）
Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that some geometric consequences of adversarial training on the decision boundary of deep networks give an edge to certain types of black-box attacks. In particular, we define a metric called robustness gain to show that while adversarial training is an effective method to dramatically improve the robustness in white-box scenarios, it may not provide such a good r…
CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全研究中心）
Machine learning models are now widely deployed in real-world applications. However, the existence of adversarial examples has been long considered a real threat to such models. While numerous defenses aiming to improve the robustness have been proposed, many have been shown ineffective. As these vulnerabilities are still nowhere near being eliminated, we propose an alternative deployment-based defense paradigm that goes beyond the traditional white-box and black-box threat models. Instead of training a single partially-robust model, one could train a set of same-functionality, yet, adversaria…
Recent studies have shown that adversarial examples hand-crafted on one white-box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which has raised security concerns for real-world DNNs applications. Nevertheless, existing works mostly focus on investigating the adversarial transferability across different deep models that share the same modality of input data. The cross-modal transferability of adversarial perturbation has never been explored. This paper investigates the transferability of adversarial perturba…
Massachusetts Institute of Technology（麻省理工学院）；University of California, Berkeley（加州大学伯克利分校）
Neural networks are known to be vulnerable to adversarial examples. In this note, we evaluate the two white-box defenses that appeared at CVPR 2018 and find they are ineffective: when applying existing techniques, we can reduce the accuracy of the defended models to 0%.
The Pennsylvania State University（宾夕法尼亚州立大学）；Shanghai Jiao Tong University（上海交通大学）；Amplitude（Amplitude公司）
Deep neural networks (DNNs) have been broadly adopted in health risk prediction to provide healthcare diagnoses and treatments. To evaluate their robustness, existing research conducts adversarial attacks in the white/gray-box setting where model parameters are accessible. However, a more realistic black-box adversarial attack is ignored even though most real-world models are trained with private data and released as black-box services on the cloud. To fill this gap, we propose the first black-box adversarial attack method against health risk prediction models named MedAttacker to investigate …
This work examines the vulnerability of multimodal (image + text) models to adversarial threats similar to those discussed in previous literature on unimodal (image- or text-only) models. We introduce realistic assumptions of partial model knowledge and access, and discuss how these assumptions differ from the standard "black-box"/"white-box" dichotomy common in current literature on adversarial attacks. Working under various levels of these "gray-box" assumptions, we develop new attack methodologies unique to multimodal classification and evaluate them on the Hateful Memes Challenge classific…
University of Maryland, College Park（马里兰大学帕克分校）；University of Siegen（锡根大学）
State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points. Iterative FGSM-based methods without restarts trade off performance for computational efficiency because they do not adequately explore the image space and are highly sensitive to the choice of step size. We propose a variant of Projected Gradient Descent (PGD) that uses a random step size to improve performance without resorting to expensive random restarts. Our method, Wide Iterative Stochastic crafting (WITCHcraft), achieves results superior to …
Despite significant improvements in natural language understanding models with the advent of models like BERT and XLNet, these neural-network based classifiers are vulnerable to blackbox adversarial attacks, where the attacker is only allowed to query the target model outputs. We add two more realistic restrictions on the attack methods, namely limiting the number of queries allowed (query budget) and crafting attacks that easily transfer across different pre-trained models (transferability), which render previous attack models impractical and ineffective. Here, we propose a target model agnos…
Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adversarial perturbations imperceptible is especially challenging for transfer-based black-box adversarial attacks. Often such adversarial examples can be easily spotted due to their unpleasantly poor visual qualities, which compromises the threat of adversarial attacks in practice. In this study, to improve the image quality of black-box adversarial examples perceptually, we propos…
Central South University（中南大学）；National University of Defence Technology（国防科技大学）；Tsinghua University（清华大学）
Hypergraph neural networks (HGNN) have shown superior performance in various deep learning tasks, leveraging the high-order representation ability to formulate complex correlations among data by connecting two or more nodes through hyperedge modeling. Despite the well-studied adversarial attacks on Graph Neural Networks (GNN), there is few study on adversarial attacks against HGNN, which leads to a threat to the safety of HGNN applications. In this paper, we introduce HyperAttack, the first white-box adversarial attack framework against hypergraph neural networks. HyperAttack conducts a white-…
Deep neural network classifiers suffer from adversarial vulnerability: well-crafted, unnoticeable changes to the input data can affect the classifier decision. In this regard, the study of powerful adversarial attacks can help shed light on sources of this malicious behavior. In this paper, we propose a novel black-box adversarial attack using normalizing flows. We show how an adversary can be found by searching over a pre-trained flow-based model base distribution. This way, we can generate adversaries that resemble the original data closely as the perturbations are in the shape of the data. …
Pennsylvania State University（宾夕法尼亚州立大学）；Applied Research Solutions（应用研究解决方案公司）；Air Force Research Lab（空军研究实验室）
Bayesian Neural Networks (BNNs), unlike Traditional Neural Networks (TNNs) are robust and adept at handling adversarial attacks by incorporating randomness. This randomness improves the estimation of uncertainty, a feature lacking in TNNs. Thus, we investigate the robustness of BNNs to white-box attacks using multiple Bayesian neural architectures. Furthermore, we create our BNN model, called BNN-DenseNet, by fusing Bayesian inference (i.e., variational Bayes) to the DenseNet architecture, and BDAV, by combining this intervention with adversarial training. Experiments are conducted on the CIFA…
The vulnerability of the high-performance machine learning models implies a security risk in applications with real-world consequences. Research on adversarial attacks is beneficial in guiding the development of machine learning models on the one hand and finding targeted defenses on the other. However, most of the adversarial attacks today leverage the gradient or logit information from the models to generate adversarial perturbation. Works in the more realistic domain: decision-based attacks, which generate adversarial perturbation solely based on observing the output label of the targeted m…
Wuhan University（武汉大学）；Pennsylvania State University（宾夕法尼亚州立大学）
Adversarial examples are well-designed input samples, in which perturbations are imperceptible to the human eyes, but easily mislead the output of deep neural networks (DNNs). Existing works synthesize adversarial examples by leveraging simple metrics to penalize perturbations, that lack sufficient consideration of the human visual system (HVS), which produces noticeable artifacts. To explore why the perturbations are visible, this paper summarizes four primary factors affecting the perceptibility of human eyes. Based on this investigation, we design a multi-factor metric MulFactorLoss for mea…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Tencent AI Lab（腾讯人工智能实验室）
This work studies black-box adversarial attacks against deep neural networks (DNNs), where the attacker can only access the query feedback returned by the attacked DNN model, while other information such as model parameters or the training datasets are unknown. One promising approach to improve attack performance is utilizing the adversarial transferability between some white-box surrogate models and the target model (i.e., the attacked model). However, due to the possible differences on model architectures and training datasets between surrogate and target models, dubbed "surrogate biases", t…
We propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-art success rate and query efficiency for multiple sparse attack models: $l_0$-bounded perturbations, adversarial patches, and adversarial frames. The $l_0$-version of untargeted Sparse-RS outperforms all black-box and even all white-box attacks for different models on MNIST, CIFAR-10, and ImageNet. Moreover, our untargeted Sparse-RS achieves very high success rates even for th…
Southern University of Science and Technology（南方科技大学）；The Hong Kong Polytechnic University（香港理工大学）
Deep neural networks are vulnerable to adversarial examples, even in the black-box setting where the attacker is only accessible to the model output. Recent studies have devised effective black-box attacks with high query efficiency. However, such performance is often accompanied by compromises in attack imperceptibility, hindering the practical use of these approaches. In this paper, we propose to restrict the perturbations to a small salient region to generate adversarial examples that can hardly be perceived. This approach is readily compatible with many existing black-box attacks and can s…
Deep neural networks are widely used in various fields because of their powerful performance. However, recent studies have shown that deep learning models are vulnerable to adversarial attacks, i.e., adding a slight perturbation to the input will make the model obtain wrong results. This is especially dangerous for some systems with high-security requirements, so this paper proposes a new defense method by using the model super-fitting state to improve the model's adversarial robustness (i.e., the accuracy under adversarial attacks). This paper mathematically proves the effectiveness of super-…
Adversarial attacks have threatened the application of deep neural networks in security-sensitive scenarios. Most existing black-box attacks fool the target model by interacting with it many times and producing global perturbations. However, global perturbations change the smooth and insignificant background, which not only makes the perturbation more easily be perceived but also increases the query overhead. In this paper, we propose a novel framework to perturb the discriminative areas of clean examples only within limited queries in black-box attacks. Our framework is constructed based on t…
Since Biggio et al. (2013) and Szegedy et al. (2013) first drew attention to adversarial examples, there has been a flood of research into defending and attacking machine learning models. However, almost all proposed attacks assume white-box access to a model. In other words, the attacker is assumed to have perfect knowledge of the models weights and architecture. With this insider knowledge, a white-box attack can leverage gradient information to craft adversarial examples. Black-box attacks assume no knowledge of the model weights or architecture. These attacks craft adversarial examples usi…
ByteDance AI Lab（字节跳动人工智能实验室）；University of California, Davis（加州大学戴维斯分校）
The vulnerability of deep neural networks (DNNs) to adversarial examples has drawn great attention from the community. In this paper, we study the transferability of such examples, which lays the foundation of many black-box attacks on DNNs. We revisit a not so new but definitely noteworthy hypothesis of Goodfellow et al.'s and disclose that the transferability can be enhanced by improving the linearity of DNNs in an appropriate manner. We introduce linear backpropagation (LinBP), a method that performs backpropagation in a more linear fashion using off-the-shelf attacks that exploit gradients…
Machine learning has been used to detect new malware in recent years, while malware authors have strong motivation to attack such algorithms. Malware authors usually have no access to the detailed structures and parameters of the machine learning models used by malware detection systems, and therefore they can only perform black-box attacks. This paper proposes a generative adversarial network (GAN) based algorithm named MalGAN to generate adversarial malware examples, which are able to bypass black-box machine learning based detection models. MalGAN uses a substitute detector to fit the black…
With the fast development of machine learning technologies, deep learning models have been deployed in almost every aspect of everyday life. However, the privacy and security of these models are threatened by adversarial attacks. Among which black-box attack is closer to reality, where limited knowledge can be acquired from the model. In this paper, we provided basic background knowledge about adversarial attack and analyzed four black-box attack algorithms: Bandits, NES, Square Attack and ZOsignSGD comprehensively. We also explored the newly proposed Square Attack method with respect to squar…
University of Central Florida（中佛罗里达大学）；Hong Kong University of Science and Technology（香港科技大学）；Google（谷歌）
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we propose a black-box adversarial attack algorithm that can defeat both vanilla DNNs and those generated by various defense techniques developed recently. Instead of searching for an "optimal" adversarial example for a benign input to a targeted DNN, our algorithm finds a probability density distribution over a small region centered around the input, such that a sample drawn from this distribution is likely an adversa…
In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for transforming images to adversarial perturbations. Our proposed models can produce image-agnostic and image-dependent perturbations for both targeted and non-targeted attacks. We also demonstrate that similar architectures can achieve impressive results in fooling classification and semantic segmentation models, obviating the need for hand-crafting attack methods …
Deep learning (DL), despite its enormous success in many computer vision and language processing applications, is exceedingly vulnerable to adversarial attacks. We consider the use of DL for radio signal (modulation) classification tasks, and present practical methods for the crafting of white-box and universal black-box adversarial attacks in that application. We show that these attacks can considerably reduce the classification performance, with extremely small perturbations of the input. In particular, these attacks are significantly more powerful than classical jamming attacks, which raise…
We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient either by using a transfer gradient of a surrogate white-box model, or based on the query feedback. However, these methods often suffer from low attack success rates or poor query efficiency since it is non-trivial to estimate the gradient in a high-dimensional space with limited information. To address these problems, we propose a prior-guided random gradient-free (P-RGF) method…
Deep Neural Networks (DNNs) are being used in various daily tasks such as object detection, speech processing, and machine translation. However, it is known that DNNs suffer from robustness problems -- perturbed inputs called adversarial samples leading to misbehaviors of DNNs. In this paper, we propose a black-box technique called Black-box Momentum Iterative Fast Gradient Sign Method (BMI-FGSM) to test the robustness of DNN models. The technique does not require any knowledge of the structure or weights of the target DNN. Compared to existing white-box testing techniques that require accessi…
fortiss GmbH（福蒂斯有限公司）；Technical University of Munich（慕尼黑工业大学）
Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail. We show that the choice of starting points is indeed crucial, and that the performance of state-of-the-art attacks depends on it. First, we discuss desirable properties of starting points for attacking image classifiers, and how they can be chosen to increase query efficiency. Notably, we find that simply copying small patches from other images is a valid strategy. We then present an evaluation on ImageNet that clearl…
