Adversarial examples are a type of attack on machine learning (ML) systems which cause misclassification of inputs. Achieving robustness against adversarial examples is crucial to apply ML in the real world. While most prior work on adversarial examples is empirical, a recent line of work establishes fundamental limitations of robust classification based on cryptographic hardness. Most positive and negative results in this field however assume that there is a fixed target metric which constrains the adversary, and we argue that this is often an unrealistic assumption. In this work we study the limitations of robust classification if the target metric is uncertain. Concretely, we construct a classification problem, which admits robust classification by a small classifier if the target metric is known at the time the model is trained, but for which robust classification is impossible for small classifiers if the target metric is chosen after the fact. In the process, we explore a novel connection between hardness of robust classification and bounded storage model cryptography.
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；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）
Deep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-trained model can be easily attacked by adding small perturbations to the original data. One of the hypotheses of the existence of the adversarial examples is the off-manifold assumption: adversarial examples lie off the data manifold. However, recent research showed that on-manifold adversarial examples also exist. In this paper, we revisit the off-manifold assumption and want to study a question: at what level is the poor performance of neural networks against adversarial attacks due to on-manifold adversa…
Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities. Despite significant recent work on adversarial example generation targeting image classifiers, relatively little work exists exploring adversarial example generation for text classifiers; additionally, many existing adversarial example generation algorithms require full access to target model parameters, rendering them impractical for many real-world attacks. In…
South China University of Technology（华南理工大学）；ETH Zürich（苏黎世联邦理工学院）；National University of Singapore（新加坡国立大学）
Deep neural networks (DNNs) are vulnerable to adversarial examples with small perturbations. Adversarial defense thus has been an important means which improves the robustness of DNNs by defending against adversarial examples. Existing defense methods focus on some specific types of adversarial examples and may fail to defend well in real-world applications. In practice, we may face many types of attacks where the exact type of adversarial examples in real-world applications can be even unknown. In this paper, motivated by that adversarial examples are more likely to appear near the classifica…
Eindhoven University of Technology（埃因霍温理工大学）；National University of Singapore（新加坡国立大学）
Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters are available. Finding adversarial examples that are transferable to other models or developed in a black-box setting is significantly more difficult. In this paper, we propose the Direction-Aggregated adversarial attacks that deliver transferable adversarial examples. Our method utilizes aggregated direction during the attack process for avoiding the generat…
Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images. This security vulnerability has led to vast research in recent years because it can introduce real-world threats into systems that rely on neural networks. Yet, a deep understanding of the characteristics of adversarial examples has remained elusive. We propose a new way of achieving such understanding through a recent development, namely, invertible neural models with Lipschitz continuous mapping functions from the input to the output. With th…
Wuhan University（武汉大学）；Chinese University of Hong Kong（香港中文大学）；Pennsylvania State University（宾夕法尼亚州立大学）
Although deep neural networks (DNNs) have shown impressive performance on many perceptual tasks, they are vulnerable to adversarial examples that are generated by adding slight but maliciously crafted perturbations to benign images. Adversarial detection is an important technique for identifying adversarial examples before they are entered into target DNNs. Previous studies to detect adversarial examples either targeted specific attacks or required expensive computation. How design a lightweight unsupervised detector is still a challenging problem. In this paper, we propose an AutoEncoder-base…
University of Maryland（马里兰大学）；University of Siegen（锡根大学）
The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained models, are even more effective for data poisoning than recent methods designed specifically for poisoning. Our findings indicate that adversarial examples, when assigned the original label of their natural base image, cannot be used to train a classifier for natural images. Furthermore, when adversarial examples are assigned their adversarial class label, th…
Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such that its corresponding model output changes. These sensitivity attacks exploit the model's sensitivity toward task-irrelevant features. Another form of adversarial sample can be crafted via invariance attacks, which exploit the model underestimating the importance of relevant features. Previous literature has indicated a tradeoff in defending against both a…
Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy multiple simultaneous constraints often over-optimize against one constraint at the cost of satisfying another. We introduce Orthogonal Projected Gradient Descent, an improved attack technique to generate adversarial examples that avoids this problem by orthogonalizing the gradients when running standard gradient-based attacks. We use our technique to evade fo…
Cornell Tech（康奈尔科技）；University of Montreal（蒙特利尔大学）；Deepmind；Carnegie-Mellon University（卡内基梅隆大学）；Stanford University（斯坦福大学）
Modern classification algorithms are susceptible to adversarial examples--perturbations to inputs that cause the algorithm to produce undesirable behavior. In this work, we seek to understand and extend adversarial examples across domains in which inputs are discrete, particularly across new domains, such as computational biology. As a step towards this goal, we formalize a notion of synonymous adversarial examples that applies in any discrete setting and describe a simple domain-agnostic algorithm to construct such examples. We apply this algorithm across multiple domains--including sentiment…
Technical University of Munich（慕尼黑工业大学）；University of Maryland, College Park（马里兰大学帕克分校）
Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attack over the examples according to the underlying data distribution, which is apparently unrealistic as the attacker could choose to focus on more vulnerable examples. We present a weighted minimax risk optimization that defends against non-uniform attacks, achieving robustness against adversarial examples under perturbed test data distributions. Our modified risk considers impor…
MagNet and "Efficient Defenses..." were recently proposed as a defense to adversarial examples. We find that we can construct adversarial examples that defeat these defenses with only a slight increase in distortion.
Neural networks work remarkably well in practice and theoretically they can be universal approximators. However, they still make mistakes and a specific type of them called adversarial errors seem inexcusable to humans. In this work, we analyze both test errors and adversarial errors on a well controlled but highly non-linear visual classification problem. We find that, when approximating training on infinite data, test errors tend to be close to the ground truth decision boundary. Qualitatively speaking these are also more difficult for a human. By contrast, adversarial examples can be found …
University of Technology Sydney（悉尼科技大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）；The University of Sydney（悉尼大学）
Deep Neural Networks (DNNs) have recently achieved great success in many tasks, which encourages DNNs to be widely used as a machine learning service in model sharing scenarios. However, attackers can easily generate adversarial examples with a small perturbation to fool the DNN models to predict wrong labels. To improve the robustness of shared DNN models against adversarial attacks, we propose a novel method called Latent Adversarial Defence (LAD). The proposed LAD method improves the robustness of a DNN model through adversarial training on generated adversarial examples. Different from pop…
Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved. In order to avoid model collapse due to excessively hard examples, the existing defenses dismiss the min-max adversarial training, but instead learn from a weak adversary inefficiently. Conversely, we propose Hardness Manipulation to efficiently perturb the training triplet till a specified level of hardness for adversarial training, according to a harder benign triplet or a pseudo-hardness function. It is flexible since regular training and min-max adversarial…
Department of Electrical and Computer Engineering, University of Illinois at Chicago（伊利诺伊大学芝加哥分校电气与计算机工程系）；Kitware Inc.（Kitware公司）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
Deep Neural Networks(DNN) have excessively advanced the field of computer vision by achieving state of the art performance in various vision tasks. These results are not limited to the field of vision but can also be seen in speech recognition and machine translation tasks. Recently, DNNs are found to poorly fail when tested with samples that are crafted by making imperceptible changes to the original input images. This causes a gap between the validation and adversarial performance of a DNN. An effective and generalizable robustness metric for evaluating the performance of DNN on these advers…
Huazhong University of Science and Technology（华中科技大学）；Peking University（北京大学）；Cornell University（康奈尔大学）
Despite the rapid development of adversarial machine learning, most adversarial attack and defense researches mainly focus on the perturbation-based adversarial examples, which is constrained by the input images. In comparison with existing works, we propose non-constrained adversarial examples, which are generated entirely from scratch without any constraint on the input. Unlike perturbation-based attacks, or the so-called unrestricted adversarial attack which is still constrained by the input noise, we aim to learn the distribution of adversarial examples to generate non-constrained but sema…
State-of-art deep neural networks (DNN) are vulnerable to attacks by adversarial examples: a carefully designed small perturbation to the input, that is imperceptible to human, can mislead DNN. To understand the root cause of adversarial examples, we quantify the probability of adversarial example existence for linear classifiers. Previous mathematical definition of adversarial examples only involves the overall perturbation amount, and we propose a more practical relevant definition of strong adversarial examples that separately limits the perturbation along the signal direction also. We show…
Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to shift closer to the "false" class. Motivated by this observation, we propose to regularize the representation space under attack with metric learning to produce more robust classifiers. By carefully sampling examples for metric learning, our learned representation not only increases robustness, but also detects previously unseen adversarial samples. Quantita…
Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics
College of Information Science and Engineering, Northeastern University（东北大学信息科学与工程学院）；Foshan Graduate School, Northeastern University（东北大学佛山研究生院）；College of Control Science and Engineering, Zhejiang University（浙江大学控制科学与工程学院）
Zhejiang University of Science and Technology（浙江科技大学）；Hikvision Digital Technology Co., Ltd（海康威视数字技术股份有限公司）；Guangzhou University（广州大学）；CY Cergy Paris University（CY塞尔吉-巴黎大学）
Recent studies show deep neural networks (DNNs) are extremely vulnerable to the elaborately designed adversarial examples. Adversarial learning with those adversarial examples has been proved as one of the most effective methods to defend against such an attack. At present, most existing adversarial examples generation methods are based on first-order gradients, which can hardly further improve models' robustness, especially when facing second-order adversarial attacks. Compared with first-order gradients, second-order gradients provide a more accurate approximation of the loss landscape with …
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…
New Jersey Institute of Technology（新泽西理工学院）；Qatar Computing Research Institute（卡塔尔计算研究所）
Adversarial examples have become one of the largest challenges that machine learning models, especially neural network classifiers, face. These adversarial examples break the assumption of attack-free scenario and fool state-of-the-art (SOTA) classifiers with insignificant perturbations to human. So far, researchers achieved great progress in utilizing adversarial training as a defense. However, the overwhelming computational cost degrades its applicability and little has been done to overcome this issue. Single-Step adversarial training methods have been proposed as computationally viable sol…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）
Correctly classifying adversarial examples is an essential but challenging requirement for safely deploying machine learning models. As reported in RobustBench, even the state-of-the-art adversarially trained models struggle to exceed 67% robust test accuracy on CIFAR-10, which is far from practical. A complementary way towards robustness is to introduce a rejection option, allowing the model to not return predictions on uncertain inputs, where confidence is a commonly used certainty proxy. Along with this routine, we find that confidence and a rectified confidence (R-Con) can form two coupled…
Recent research has proved that deep neural networks (DNNs) are vulnerable to adversarial examples, the legitimate input added with imperceptible and well-designed perturbations can fool DNNs easily in the testing stage. However, most of the existing adversarial attacks are difficult to fool adversarially trained models. To solve this issue, we propose an AdaBelief iterative Fast Gradient Sign Method (AB-FGSM) to generalize adversarial examples. By integrating AdaBelief optimization algorithm to I-FGSM, we believe that the generalization of adversarial examples will be improved, relying on the…
Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）；Southern University of Science and Technology（南方科技大学）
The security issues in DNNs, such as adversarial examples, have attracted much attention. Adversarial examples refer to the examples which are capable to induce the DNNs return completely predictions by introducing carefully designed perturbations. Obviously, adversarial examples bring great security risks to the development of deep learning. Recently, Some defense approaches against adversarial examples have been proposed, however, in our opinion, the performance of these approaches are still limited. In this paper, we propose a new ensemble defense approach named the Negative Correlation Ens…
University of California, Berkeley（加州大学伯克利分校）；Stanford University（斯坦福大学）
The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques have been proposed for increasing robustness to adversarial examples --- and yet most of these have been quickly shown to be vulnerable to future attacks. For example, over half of the defenses proposed by papers accepted at ICLR 2018 have already been broken. We propose to address this difficulty through formal verification techniques. We show how to constru…
Ghent University（根特大学）；Ghent University Global Campus（根特大学全球校区）
Detecting adversarial examples currently stands as one of the biggest challenges in the field of deep learning. Adversarial attacks, which produce adversarial examples, increase the prediction likelihood of a target class for a particular data point. During this process, the adversarial example can be further optimized, even when it has already been wrongly classified with 100% confidence, thus making the adversarial example even more difficult to detect. For this kind of adversarial examples, which we refer to as over-optimized adversarial examples, we discovered that the logits of the model …
Artificial neural networks have been successfully used for many different classification tasks including malware detection and distinguishing between malicious and non-malicious programs. Although artificial neural networks perform very well on these tasks, they are also vulnerable to adversarial examples. An adversarial example is a sample that has minor modifications made to it so that the neural network misclassifies it. Many techniques have been proposed, both for crafting adversarial examples and for hardening neural networks against them. Most previous work has been done in the image dom…
With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input samples, called adversarial examples. Adversarial examples are imperceptible to human but can easily fool deep neural networks in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying deep neural networks in safety-critical environments. Therefore, attacks and defenses on adversarial examples draw …
With the excellent accuracy and feasibility, the Neural Networks have been widely applied into the novel intelligent applications and systems. However, with the appearance of the Adversarial Attack, the NN based system performance becomes extremely vulnerable:the image classification results can be arbitrarily misled by the adversarial examples, which are crafted images with human unperceivable pixel-level perturbation. As this raised a significant system security issue, we implemented a series of investigations on the adversarial attack in this work: We first identify an image's pixel vulnera…
Deep neural networks can be fooled by adversarial attacks: adding carefully computed small adversarial perturbations to clean inputs can cause misclassification on state-of-the-art machine learning models. The reason is that neural networks fail to accommodate the distribution drift of the input data caused by adversarial perturbations. Here, we present a new solution - Beneficial Perturbation Network (BPN) - to defend against adversarial attacks by fixing the distribution drift. During training, BPN generates and leverages beneficial perturbations (somewhat opposite to well-known adversarial …
University of Virginia（弗吉尼亚大学）；HRL Laboratories, LLC.（HRL实验室有限责任公司）
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains. Devising a definitive defense against such attacks is proven to be challenging, and the methods relying on detecting adversarial samples are only valid when the attacker is oblivious to the detection mechanism. In this paper we propose a principled adversarial example detection method that can withstand norm-constrained white-box attacks. Inspired by one-versus-the-rest classification, in a K class classification problem, we train K binary …
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 …
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…
I introduce a very simple method to defend against adversarial examples. The basic idea is to raise the slope of the ReLU function at the test time. Experiments over MNIST and CIFAR-10 datasets demonstrate the effectiveness of the proposed defense against a number of strong attacks in both untargeted and targeted settings. While perhaps not as effective as the state of the art adversarial defenses, this approach can provide insights to understand and mitigate adversarial attacks. It can also be used in conjunction with other defenses.
Adversarial examples are artificially modified input samples which lead to misclassifications, while not being detectable by humans. These adversarial examples are a challenge for many tasks such as image and text classification, especially as research shows that many adversarial examples are transferable between different classifiers. In this work, we evaluate the performance of a popular defensive strategy for adversarial examples called defensive distillation, which can be successful in hardening neural networks against adversarial examples in the image domain. However, instead of applying …
University of Michigan（密歇根大学）；Simon Fraser University（西蒙弗雷泽大学）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；UC Berkeley（加州大学伯克利分校）
Deep Neural Networks (DNNs) have been widely applied in various recognition tasks. However, recently DNNs have been shown to be vulnerable against adversarial examples, which can mislead DNNs to make arbitrary incorrect predictions. While adversarial examples are well studied in classification tasks, other learning problems may have different properties. For instance, semantic segmentation requires additional components such as dilated convolutions and multiscale processing. In this paper, we aim to characterize adversarial examples based on spatial context information in semantic segmentation…
We propose a new ensemble method for detecting and classifying adversarial examples generated by state-of-the-art attacks, including DeepFool and C&W. Our method works by training the members of an ensemble to have low classification error on random benign examples while simultaneously minimizing agreement on examples outside the training distribution. We evaluate on both MNIST and CIFAR-10, against oblivious and both white- and black-box adversaries.
We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50 characters per second of audio). We apply our white-box iterative optimization-based attack to Mozilla's implementation DeepSpeech end-to-end, and show it has a 100% success rate. The feasibility of this attack introduce a new domain to study adversarial examples.
We provide a complete characterisation of the phenomenon of adversarial examples - inputs intentionally crafted to fool machine learning models. We aim to cover all the important concerns in this field of study: (1) the conjectures on the existence of adversarial examples, (2) the security, safety and robustness implications, (3) the methods used to generate and (4) protect against adversarial examples and (5) the ability of adversarial examples to transfer between different machine learning models. We provide ample background information in an effort to make this document self-contained. Ther…
State-of-the-art deep neural networks (DNNs) are highly effective in solving many complex real-world problems. However, these models are vulnerable to adversarial perturbation attacks, and despite the plethora of research in this domain, to this day, adversaries still have the upper hand in the cat and mouse game of adversarial example generation methods vs. detection and prevention methods. In this research, we present a novel detection method that uses Shapley Additive Explanations (SHAP) values computed for the internal layers of a DNN classifier to discriminate between normal and adversari…
Adversarial pruning compresses models while preserving robustness. Current methods require access to adversarial examples during pruning. This significantly hampers training efficiency. Moreover, as new adversarial attacks and training methods develop at a rapid rate, adversarial pruning methods need to be modified accordingly to keep up. In this work, we propose a novel framework to prune a previously trained robust neural network while maintaining adversarial robustness, without further generating adversarial examples. We leverage concurrent self-distillation and pruning to preserve knowledg…
Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on machine learning models in the visual domain, where methods for generating and detecting such examples have been most extensively studied. We explore a variety of adversarial attack methods that apply to image-space content, real world adversarial attacks, adversarial defenses, and the transferability property of adversarial examples. We also discuss strengths and…
With the rapid development of Artificial Intelligence (AI), the problem of AI security has gradually emerged. Most existing machine learning algorithms may be attacked by adversarial examples. An adversarial example is a slightly modified input sample that can lead to a false result of machine learning algorithms. The adversarial examples pose a potential security threat for many AI application areas, especially in the domain of robot path planning. In this field, the adversarial examples obstruct the algorithm by adding obstacles to the normal maps, resulting in multiple effects on the predic…
This article presents a summary of a keynote lecture at the Deep Learning Security workshop at IEEE Security and Privacy 2018. This lecture summarizes the state of the art in defenses against adversarial examples and provides recommendations for future research directions on this topic.
Thanks to recent advances in deep neural networks (DNNs), face recognition systems have become highly accurate in classifying a large number of face images. However, recent studies have found that DNNs could be vulnerable to adversarial examples, raising concerns about the robustness of such systems. Adversarial examples that are not restricted to small perturbations could be more serious since conventional certified defenses might be ineffective against them. To shed light on the vulnerability to such adversarial examples, we propose a flexible and efficient method for generating unrestricted…
College of Information Science and Engineering, Ningbo University（宁波大学信息科学与工程学院）
Speech is easily leaked imperceptibly, such as being recorded by mobile phones in different situations. Private content in speech may be maliciously extracted through speech enhancement technology. Speech enhancement technology has developed rapidly along with deep neural networks (DNNs), but adversarial examples can cause DNNs to fail. In this work, we propose an adversarial method to degrade speech enhancement systems. Experimental results show that generated adversarial examples can erase most content information in original examples or replace it with target speech content through speech e…
National Chung Hsing University（国立中兴大学）；IBM Research（IBM研究院）
Understanding and characterizing the subspaces of adversarial examples aid in studying the robustness of deep neural networks (DNNs) to adversarial perturbations. Very recently, Ma et al. (ICLR 2018) proposed to use local intrinsic dimensionality (LID) in layer-wise hidden representations of DNNs to study adversarial subspaces. It was demonstrated that LID can be used to characterize the adversarial subspaces associated with different attack methods, e.g., the Carlini and Wagner's (C&W) attack and the fast gradient sign attack. In this paper, we use MNIST and CIFAR-10 to conduct two new sets o…
It has been shown that adversaries can craft example inputs to neural networks which are similar to legitimate inputs but have been created to purposely cause the neural network to misclassify the input. These adversarial examples are crafted, for example, by calculating gradients of a carefully defined loss function with respect to the input. As a countermeasure, some researchers have tried to design robust models by blocking or obfuscating gradients, even in white-box settings. Another line of research proposes introducing a separate detector to attempt to detect adversarial examples. This a…
