This paper will describe and analyze a new phenomenon that was not known before, which we call "Early Transferability". Its essence is that the adversarial perturbations transfer among different networks even at extremely early stages in their training. In fact, one can initialize two networks with two different independent choices of random weights and measure the angle between their adversarial perturbations after each step of the training. What we discovered was that these two adversarial directions started to align with each other already after the first few training steps (which typically use only a small fraction of the available training data), even though the accuracy of the two networks hadn't started to improve from their initial bad values due to the early stage of the training. The purpose of this paper is to present this phenomenon experimentally and propose plausible explanations for some of its properties.
Adversarial transferability, namely the ability of adversarial perturbations to simultaneously fool multiple learning models, has long been the "big bad wolf" of adversarial machine learning. Successful transferability-based attacks requiring no prior knowledge of the attacked model's parameters or training data have been demonstrated numerous times in the past, implying that machine learning models pose an inherent security threat to real-life systems. However, all of the research performed in this area regarded transferability as a probabilistic property and attempted to estimate the percent…
In the last decade, the use of Machine Learning techniques in anomaly-based intrusion detection systems has seen much success. However, recent studies have shown that Machine learning in general and deep learning specifically are vulnerable to adversarial attacks where the attacker attempts to fool models by supplying deceptive input. Research in computer vision, where this vulnerability was first discovered, has shown that adversarial images designed to fool a specific model can deceive other machine learning models. In this paper, we investigate the transferability of adversarial network tra…
King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Inria（法国国家信息与自动化研究所）
Despite of the pervasive existence of multi-label evasion attack, it is an open yet essential problem to characterize the origin of the adversarial vulnerability of a multi-label learning system and assess its attackability. In this study, we focus on non-targeted evasion attack against multi-label classifiers. The goal of the threat is to cause miss-classification with respect to as many labels as possible, with the same input perturbation. Our work gains in-depth understanding about the multi-label adversarial attack by first characterizing the transferability of the attack based on the func…
Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i.e., they maintain their effectiveness even against other models. With great efforts delved into the transferability of adversarial examples, surprisingly, less attention has been paid to its impact on real-world deep learning deployment. In this paper, we investigate the transferability of adversarial examples across a wide range of real-world computer vision tasks, including image classification, explicit content detection, optical character recognition (OCR), an…
Deep learning algorithms have increasingly been shown to lack robustness to simple adversarial examples (AdvX). An equally troubling observation is that these adversarial examples transfer between different architectures trained on different datasets. We investigate the transferability of adversarial examples between models using the angle between the input-output Jacobians of different models. To demonstrate the relevance of this approach, we perform case studies that involve jointly training pairs of models. These case studies empirically justify the theoretical intuitions for why the angle …
Adversarial attacks have verified the existence of the vulnerability of neural networks. By adding small perturbations to a benign example, adversarial attacks successfully generate adversarial examples that lead misclassification of deep learning models. More importantly, an adversarial example generated from a specific model can also deceive other models without modification. We call this phenomenon ``transferability". Here, we analyze the relationship between transferability and input transformation with additive noise by mathematically proving that the modified optimization can produce mor…
Machine learning is used for inference and decision making in wearable sensor systems. However, recent studies have found that machine learning algorithms are easily fooled by the addition of adversarial perturbations to their inputs. What is more interesting is that adversarial examples generated for one machine learning system is also effective against other systems. This property of adversarial examples is called transferability. In this work, we take the first stride in studying adversarial transferability in wearable sensor systems from the following perspectives: 1) transferability betwe…
Adversarial attack transferability is well-recognized in deep learning. Prior work has partially explained transferability by recognizing common adversarial subspaces and correlations between decision boundaries, but little is known beyond this. We propose that transferability between seemingly different models is due to a high linear correlation between the feature sets that different networks extract. In other words, two models trained on the same task that are distant in the parameter space likely extract features in the same fashion, just with trivial affine transformations between the lat…
Fuzhou University（福州大学）；City University of Macau（澳门城市大学）；Peking University（北京大学）
Transferability of adversarial examples is of critical importance to launch black-box adversarial attacks, where attackers are only allowed to access the output of the target model. However, under such a challenging but practical setting, the crafted adversarial examples are always prone to overfitting to the proxy model employed, presenting poor transferability. In this paper, we suggest alleviating the overfitting issue from a novel perspective, i.e., designing a fitted model architecture. Specifically, delving the bottom of the cause of poor transferability, we arguably decompose and recons…
University of Rochester（罗切斯特大学）；Harvard University（哈佛大学）；HUST（华中科技大学）
Deep neural networks are widely known to be vulnerable to adversarial examples, especially showing significantly poor performance on adversarial examples generated under the white-box setting. However, most white-box attack methods rely heavily on the target model and quickly get stuck in local optima, resulting in poor adversarial transferability. The momentum-based methods and their variants are proposed to escape the local optima for better transferability. In this work, we notice that the transferability of adversarial examples generated by the iterative fast gradient sign method (I-FGSM) …
Tokyo Metropolitan University（东京都立大学）；National Institute of Informatics (NII)（国立信息学研究所）
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with a non-trivial probability. In this paper, we investigate the property of adversarial transferability between models including ConvMixer, which is an isotropic network, for the first time. To objectively verify the property of transferability, the robustness of models is evaluated by using a benchmark attack method called AutoAttack. In an image classificatio…
The Chinese University of Hong Kong（香港中文大学）；Sun Yat-sen University（中山大学）
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. It is thus imperative to devise effective attack algorithms to identify the deficiencies of DNNs beforehand in security-sensitive applications. To efficiently tackle the black-box setting where the target model's particulars are unknown, feature-level transfer-based attacks propose to contaminate the intermediate feature outputs of local models, and then directly employ the crafted adversarial samples to attack the target model. Due to the transferability of features, feature-level attacks have shown promise in syn…
Transferability of adversarial samples became a serious concern due to their impact on the reliability of machine learning system deployments, as they find their way into many critical applications. Knowing factors that influence transferability of adversarial samples can assist experts to make informed decisions on how to build robust and reliable machine learning systems. The goal of this study is to provide insights on the mechanisms behind the transferability of adversarial samples through an attack-centric approach. This attack-centric perspective interprets how adversarial samples would …
the University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Knowledge transferability, or transfer learning, has been widely adopted to allow a pre-trained model in the source domain to be effectively adapted to downstream tasks in the target domain. It is thus important to explore and understand the factors affecting knowledge transferability. In this paper, as the first work, we analyze and demonstrate the connections between knowledge transferability and another important phenomenon--adversarial transferability, \emph{i.e.}, adversarial examples generated against one model can be transferred to attack other models. Our theoretical studies show that …
Northeastern University（东北大学）；University of Cagliari（卡利亚里大学）；Pluribus One
Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transferability has been shown in previous work, but the underlying reasons why an attack transfers or not are not yet well understood. In this paper, we present a comprehensive analysis aimed to investigate the transferability of both test-time evasion and training-time poisoning attacks. We provide a unifying optimization framework for evasion and poisoning attacks, and a formal definition of transferability of such attacks…
With the development of adversarial attacks, adversairal examples have been widely used to enhance the robustness of the training models on deep neural networks. Although considerable efforts of adversarial attacks on improving the transferability of adversarial examples have been developed, the attack success rate of the transfer-based attacks on the surrogate model is much higher than that on victim model under the low attack strength (e.g., the attack strength $ε=8/255$). In this paper, we first systematically investigated this issue and found that the enormous difference of attack success …
Peking University（北京大学）；Beijing Institute of Big Data (BIBDR)（北京大数据研究院）；Princeton University（普林斯顿大学）
State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}: adversarial examples generated for a specific model will often mislead other unseen models. Consequently the adversary can leverage it to attack deployed systems without any query, which severely hinder the application of deep learning, especially in the areas where security is crucial. In this work, we systematically study how two classes of factors that might infl…
Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；JD Explore Academy（京东探索研究院）；Tencent AI Lab（腾讯人工智能实验室）
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples, which is significant due to its threat to real-world applications where model architecture or parameters are usually unknown. Many existing works reveal that the adversarial examples are likely to overfit the surrogate model that they are generated from, limiting its transfer attack performance against different target models. To mitigate the overfitting of the …
Although many methods have been proposed to enhance the transferability of adversarial perturbations, these methods are designed in a heuristic manner, and the essential mechanism for improving adversarial transferability is still unclear. This paper summarizes the common mechanism shared by twelve previous transferability-boosting methods in a unified view, i.e., these methods all reduce game-theoretic interactions between regional adversarial perturbations. To this end, we focus on the attacking utility of all interactions between regional adversarial perturbations, and we first discover and…
University of Luxembourg（卢森堡大学）；University of California, Berkeley（加州大学伯克利分校）
We propose transferability from Large Geometric Vicinity (LGV), a new technique to increase the transferability of black-box adversarial attacks. LGV starts from a pretrained surrogate model and collects multiple weight sets from a few additional training epochs with a constant and high learning rate. LGV exploits two geometric properties that we relate to transferability. First, models that belong to a wider weight optimum are better surrogates. Second, we identify a subspace able to generate an effective surrogate ensemble among this wider optimum. Through extensive experiments, we show that…
Improving Transferability of Adversarial Examples via Bayesian Attacks
School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；School of Mathematics and Statistics, University of Glasgow（格拉斯哥大学数学与统计学学院）；Department of Computer Science, University of California, Davis（加州大学戴维斯分校计算机科学系）
Adversarial examples are of wide concern due to their impact on the reliability of contemporary machine learning systems. Effective adversarial examples are mostly found via white-box attacks. However, in some cases they can be transferred across models, thus enabling them to attack black-box models. In this work we evaluate the transferability of three adversarial attacks - the Fast Gradient Sign Method, the Basic Iterative Method, and the Carlini & Wagner method, across two classes of models - the VGG class(using VGG16, VGG19 and an ensemble of VGG16 and VGG19), and the Inception class(Incep…
The Pennsylvania State University（宾夕法尼亚州立大学）；OpenAI
Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model, even if the two models have different architectures or were trained on different training sets, so long as both models were trained to perform the same task. An attacker may therefore train their own substitute model, craft adversarial examples against the substitute, and transfer them to a victim model, with very little information about the victim. Recent …
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…
University of Texas at Dallas（德克萨斯大学达拉斯分校）；Purdue University（普渡大学）
We investigate the role of transferability of adversarial attacks in the observed vulnerabilities of Deep Neural Networks (DNNs). We demonstrate that introducing randomness to the DNN models is sufficient to defeat adversarial attacks, given that the adversary does not have an unlimited attack budget. Instead of making one specific DNN model robust to perfect knowledge attacks (a.k.a, white box attacks), creating randomness within an army of DNNs completely eliminates the possibility of perfect knowledge acquisition, resulting in a significantly more robust DNN ensemble against the strongest f…
Université de Sousse（苏塞大学）；Ecole Nationale d’Ingénieurs de Sousse（苏塞国家工程学院）；Université polytechnique Hauts-de-France（上法兰西理工大学）；IEMN-DOAE
While machine learning applications are getting mainstream owing to a demonstrated efficiency in solving complex problems, they suffer from inherent vulnerability to adversarial attacks. Adversarial attacks consist of additive noise to an input which can fool a detector. Recently, successful real-world printable adversarial patches were proven efficient against state-of-the-art neural networks. In the transition from digital noise based attacks to real-world physical attacks, the myriad of factors affecting object detection will also affect adversarial patches. Among these factors, view angle …
University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Tencent Inc.（腾讯公司）；University of Melbourne（墨尔本大学）；Huazhong University of Science and Technology（华中科技大学）；ETH Zurich（苏黎世联邦理工学院）
Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better protect ML systems against adversarial attacks, several questions are raised: what are the sufficient conditions for adversarial transferability and how to bound it? Is there a way to reduce the adversarial transferability in order to improve the robustness of an ensemble ML model? To answer these questions, in this work we first theoretically analyze and outline …
Black-box adversarial attacks designing adversarial examples for unseen neural networks (NNs) have received great attention over the past years. While several successful black-box attack schemes have been proposed in the literature, the underlying factors driving the transferability of black-box adversarial examples still lack a thorough understanding. In this paper, we aim to demonstrate the role of the generalization properties of the substitute classifier used for generating adversarial examples in the transferability of the attack scheme to unobserved NN classifiers. To do this, we apply t…
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However, adversarial examples are typically overfit to exploit the particular architecture and feature representation of a source model, resulting in sub-optimal black-box transfer attacks to other target models. We introduce the Intermediate Level Attack (ILA), which attempts to fine-tune an existing adversarial example for greater black-box transferability by incr…
Huazhong University of Science and Technology（华中科技大学）；Cornell University（康奈尔大学）
The black-box adversarial attack has attracted impressive attention for its practical use in the field of deep learning security. Meanwhile, it is very challenging as there is no access to the network architecture or internal weights of the target model. Based on the hypothesis that if an example remains adversarial for multiple models, then it is more likely to transfer the attack capability to other models, the ensemble-based adversarial attack methods are efficient and widely used for black-box attacks. However, ways of ensemble attack are rather less investigated, and existing ensemble att…
Boosting Adversarial Transferability via Residual Perturbation Attack
School of Cyber Security and Computer（网络安全与计算机学院）；College of Information and Science Technology（信息与科学学院）；School of Computer and Information Engineering（计算机与信息工程学院）
School of Computer Science, Fudan University（复旦大学计算机学院）；Shanghai Key Laboratory of Intelligent Information Processing（上海市智能信息处理重点实验室）；Department of Computer Science, University of California, Los Angeles（加利福尼亚大学洛杉矶分校计算机科学系）
Deep neural networks are vulnerable to adversarial attacks, where a small perturbation to an input alters the model prediction. In many cases, malicious inputs intentionally crafted for one model can fool another model. In this paper, we present the first study to systematically investigate the transferability of adversarial examples for text classification models and explore how various factors, including network architecture, tokenization scheme, word embedding, and model capacity, affect the transferability of adversarial examples. Based on these studies, we propose a genetic algorithm to f…
Boosting the Transferability of Audio Adversarial Examples with Acoustic Representation Optimization
National Engineering Research Center of Disaster Backup and Recovery（国家防灾备份与恢复工程研究中心）；School of Cyberspace Security, Beijing University of Posts and Telecommunications（北京邮电大学网络空间安全学院）
Bahçeşehir University（巴赫切谢希尔大学）；University of Padua（帕多瓦大学）；Florida International University（佛罗里达国际大学）
In the past decades, the rise of artificial intelligence has given us the capabilities to solve the most challenging problems in our day-to-day lives, such as cancer prediction and autonomous navigation. However, these applications might not be reliable if not secured against adversarial attacks. In addition, recent works demonstrated that some adversarial examples are transferable across different models. Therefore, it is crucial to avoid such transferability via robust models that resist adversarial manipulations. In this paper, we propose a feature randomization-based approach that resists …
Syracuse University（雪城大学）；University of Michigan（密歇根大学）；UCLA（加州大学洛杉矶分校）；Duke University（杜克大学）
Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i.e., they remain adversarial even against other models. Although great efforts have been delved into the transferability across models, surprisingly, less attention has been paid to the cross-task transferability, which represents the real-world cybercriminal's situation, where an ensemble of different defense/detection mechanisms need to be evaded all at once. In this paper, we investigate the transferability of adversarial examples across a wide range of real-wor…
In recent years, convolutional neural networks (CNNs) have been widely used by researchers to perform forensic tasks such as image tampering detection. At the same time, adversarial attacks have been developed that are capable of fooling CNN-based classifiers. Understanding the transferability of adversarial attacks, i.e. an attacks ability to attack a different CNN than the one it was trained against, has important implications for designing CNNs that are resistant to attacks. While attacks on object recognition CNNs are believed to be transferrable, recent work by Barni et al. has shown that…
Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
School of Cyber Science and Engineering, Huazhong University of Science and Technology（电子科学与工程学院，华中科技大学）；School of Software Engineering, Huazhong University of Science and Technology（软件工程学院，华中科技大学）；School of Information and Communication Technology, Griffith University（信息与通信技术学院，格里菲斯大学）；School of Computer Science and Technology, Huazhong University of Science and Technology（计算机科学与技术学院，华中科技大学）
Vanderbilt University（范德堡大学）；Washington University in St. Louis（圣路易斯华盛顿大学）
Despite the considerable success of convolutional neural networks in a broad array of domains, recent research has shown these to be vulnerable to small adversarial perturbations, commonly known as adversarial examples. Moreover, such examples have shown to be remarkably portable, or transferable, from one model to another, enabling highly successful black-box attacks. We explore this issue of transferability and robustness from two dimensions: first, considering the impact of conventional $l_p$ regularization as well as replacing the top layer with a linear support vector machine (SVM), and s…
Raw deep neural network (DNN) performance is not enough; in real-world settings, computational load, training efficiency and adversarial security are just as or even more important. We propose to simultaneously tackle Performance, Efficiency, and Robustness, using our proposed algorithm Q-TART, Quickly Train for Adversarial Robustness and in-Transferability. Q-TART follows the intuition that samples highly susceptible to noise strongly affect the decision boundaries learned by DNNs, which in turn degrades their performance and adversarial susceptibility. By identifying and removing such sample…
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…
Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broaden the use of ML models, cloud-based services offered by Microsoft, Amazon, Google, and others have developed ML-as-a-service tools as black-box systems. However, ML classifiers are vulnerable to adversarial examples: inputs that are maliciously modified can cause the classifier to provide adversary-desired outputs. Moreover, it is known that adversarial examples generated on one classifier are likely to cause anoth…
