As research in deep neural networks advances, deep convolutional networks become promising for autonomous driving tasks. In particular, there is an emerging trend of employing end-to-end neural network models for autonomous driving. However, previous research has shown that deep neural network classifiers are vulnerable to adversarial attacks. While for regression tasks, the effect of adversarial attacks is not as well understood. In this research, we devise two white-box targeted attacks against end-to-end autonomous driving models. Our attacks manipulate the behavior of the autonomous driving system by perturbing the input image. In an average of 800 attacks with the same attack strength (epsilon=1), the image-specific and image-agnostic attack deviates the steering angle from the original output by 0.478 and 0.111, respectively, which is much stronger than random noises that only perturbs the steering angle by 0.002 (The steering angle ranges from [-1, 1]). Both attacks can be initiated in real-time on CPUs without employing GPUs. Demo video: https://youtu.be/I0i8uN2oOP0.
Valeo R&D Egypt（法雷奥研发埃及）；Valeo DAR Germany（法雷奥DAR德国）；Technische Universität Ilmenau（伊尔梅瑙工业大学）；Valeo Ireland（法雷奥爱尔兰）
Deep neural networks (DNNs) have accomplished impressive success in various applications, including autonomous driving perception tasks, in recent years. On the other hand, current deep neural networks are easily fooled by adversarial attacks. This vulnerability raises significant concerns, particularly in safety-critical applications. As a result, research into attacking and defending DNNs has gained much coverage. In this work, detailed adversarial attacks are applied on a diverse multi-task visual perception deep network across distance estimation, semantic segmentation, motion detection, a…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Tübingen（蒂宾根大学）
Deep neural nets achieve state-of-the-art performance on the problem of optical flow estimation. Since optical flow is used in several safety-critical applications like self-driving cars, it is important to gain insights into the robustness of those techniques. Recently, it has been shown that adversarial attacks easily fool deep neural networks to misclassify objects. The robustness of optical flow networks to adversarial attacks, however, has not been studied so far. In this paper, we extend adversarial patch attacks to optical flow networks and show that such attacks can compromise their pe…
Washington University in St. Louis（圣路易斯华盛顿大学）；University of Michigan, Ann Arbor（密歇根大学安娜堡分校）
Recent advances in machine learning, especially techniques such as deep neural networks, are enabling a range of emerging applications. One such example is autonomous driving, which often relies on deep learning for perception. However, deep learning-based perception has been shown to be vulnerable to a host of subtle adversarial manipulations of images. Nevertheless, the vast majority of such demonstrations focus on perception that is disembodied from end-to-end control. We present novel end-to-end attacks on autonomous driving in simulation, using simple physically realizable attacks: the pa…
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transferability and are easy to defend. To address these problems, in this paper we propose a novel point cloud attack (dubbed AOF) that pays more attention on the low-frequency component of point clouds. We combine the losses from point cloud and its low-frequency component to craft adversarial samples. Extensive experiments…
Recent studies reveal that Convolutional Neural Networks (CNNs) are typically vulnerable to adversarial attacks, which pose a threat to security-sensitive applications. Many adversarial defense methods improve robustness at the cost of accuracy, raising the contradiction between standard and adversarial accuracies. In this paper, we observe an interesting phenomenon that feature statistics change monotonically and smoothly w.r.t the rising of attacking strength. Based on this observation, we propose the adaptive feature alignment (AFA) to generate features of arbitrary attacking strengths. Our…
Singtel Cognitive and Artificial Intelligence Lab for Enterprises（Singtel企业认知与人工智能实验室）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe overfitting (than classical supervised learning) as the supervised source loss has clear domain gap and the unsupervised target loss is often noisy due to the lack of annotations. This paper presents RDA, a robust domain adaptation technique that introduces adversarial attacking to mitigate overfitting in UDA. We achieve robust domain adaptation by a novel Fourier adversarial attacking (FAA) method that allows large mag…
MIT（麻省理工学院）；IBM Research（IBM研究院）；JD AI Research（京东人工智能研究院）；UC Davis（加州大学戴维斯分校）
Visual language grounding is widely studied in modern neural image captioning systems, which typically adopts an encoder-decoder framework consisting of two principal components: a convolutional neural network (CNN) for image feature extraction and a recurrent neural network (RNN) for language caption generation. To study the robustness of language grounding to adversarial perturbations in machine vision and perception, we propose Show-and-Fool, a novel algorithm for crafting adversarial examples in neural image captioning. The proposed algorithm provides two evaluation approaches, which check…
Convolutional Neural Networks (CNNs) are vulnerable to misclassifying images when small perturbations are present. With the increasing prevalence of CNNs in self-driving cars, it is vital to ensure these algorithms are robust to prevent collisions from occurring due to failure in recognizing a situation. In the Adversarial Self-Driving framework, a Generative Adversarial Network (GAN) is implemented to generate realistic perturbations in an image that cause a classifier CNN to misclassify data. This perturbed data is then used to train the classifier CNN further. The Adversarial Self-driving f…
Current adversarial attacks for motion estimation (optical flow) optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, we exploit a real-world weather phenomenon for a novel attack with adversarially optimized snow. At the core of our attack is a differentiable renderer that consistently integrates photorealistic snowflakes with realistic motion into the 3D scene. Through optimization we obtain adversarial snow that significantly impacts the optical flow while being indistinguishable from ordinary snow. Surprisingly, the impact of our novel attack…
Fudan University（复旦大学）；Shanghai Key Lab of Intelligent Information Processing（上海市智能信息处理重点实验室）；Shanghai Collaborative Innovation Center on Intelligent Visual Computing（上海智能视觉计算协同创新中心）
Recent research has demonstrated that Deep Neural Networks (DNNs) are vulnerable to adversarial patches which introduce perceptible but localized changes to the input. Nevertheless, existing approaches have focused on generating adversarial patches on images, their counterparts in videos have been less explored. Compared with images, attacking videos is much more challenging as it needs to consider not only spatial cues but also temporal cues. To close this gap, we introduce a novel adversarial attack in this paper, the bullet-screen comment (BSC) attack, which attacks video recognition models…
Chengdu University of Information Technology（成都信息工程大学）；Carnegie Mellon University（卡内基梅隆大学）；University at Buffalo, SUNY（纽约州立大学布法罗分校）；Microsoft Research Asia（微软亚洲研究院）
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change the prediction result. Existing adversarial attacks on object detection focus on attacking anchor-based detectors, which may not work well for anchor-free detectors. In this paper, we propose the first adversarial attack dedicated to anchor-free detectors. It is a category-wise attack that attacks important pixels of all instances of a category simultaneously. Our attack manifests in two forms, sparse category-wise attack (SCA) and dense category-wise attack (DCA), tha…
Adversarial attacks are often considered as threats to the robustness of Deep Neural Networks (DNNs). Various defending techniques have been developed to mitigate the potential negative impact of adversarial attacks against task predictions. This work analyzes adversarial attacks from a different perspective. Namely, adversarial examples contain implicit information that is useful to the predictions i.e., image classification, and treat the adversarial attacks against DNNs for data self-expression as extracted abstract representations that are capable of facilitating specific learning tasks. W…
Fraunhofer HHI（弗劳恩霍夫电信研究所）；TU Berlin（柏林工业大学）；Berlin Big Data Center（柏林大数据中心）；Korea University（高丽大学）；MPI for Informatics（马克斯·普朗克信息学研究所）；RIKEN AIP（理化学研究所先进智能项目中心）
Developing techniques for adversarial attack and defense is an important research field for establishing reliable machine learning and its applications. Many existing methods employ Gaussian random variables for exploring the data space to find the most adversarial (for attacking) or least adversarial (for defense) point. However, the Gaussian distribution is not necessarily the optimal choice when the exploration is required to follow the complicated structure that most real-world data distributions exhibit. In this paper, we investigate how statistics of random variables affect such random w…
Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Tsinghua University（清华大学）
Optical character recognition (OCR) is widely applied in real applications serving as a key preprocessing tool. The adoption of deep neural network (DNN) in OCR results in the vulnerability against adversarial examples which are crafted to mislead the output of the threat model. Different from vanilla colorful images, images of printed text have clear backgrounds usually. However, adversarial examples generated by most of the existing adversarial attacks are unnatural and pollute the background severely. To address this issue, we propose a watermark attack method to produce natural distortion …
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Oxford（牛津大学）；Kuaishou Technology（快手科技）；ByteDance Research（字节跳动研究院）
This paper focuses on learning transferable adversarial examples specifically against defense models (models to defense adversarial attacks). In particular, we show that a simple universal perturbation can fool a series of state-of-the-art defenses. Adversarial examples generated by existing attacks are generally hard to transfer to defense models. We observe the property of regional homogeneity in adversarial perturbations and suggest that the defenses are less robust to regionally homogeneous perturbations. Therefore, we propose an effective transforming paradigm and a customized gradient tr…
Beihang University（北京航空航天大学）；Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）
Adversarial attacks on video recognition models have been explored recently. However, most existing works treat each video frame equally and ignore their temporal interactions. To overcome this drawback, a few methods try to select some key frames and then perform attacks based on them. Unfortunately, their selection strategy is independent of the attacking step, therefore the resulting performance is limited. Instead, we argue the frame selection phase is closely relevant with the attacking phase. The key frames should be adjusted according to the attacking results. For that, we formulate the…
Chengdu University of Information Technology（成都信息工程大学）；CuraCloud Corporation（库拉云公司）；SUNY Albany（纽约州立大学奥尔巴尼分校）
The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object detectors, but they generate globally perturbation on the whole image, which is unnecessary. In our work, we leverage higher-level semantic information to generate high aggressive local perturbations for anchor-free object detectors. As a result, it is less computationally intensive and achieves a higher black-box attack as well as transferring attack performance.…
Vision and Security Technology (VAST) Lab（视觉与安全技术（VAST）实验室）；University of Colorado, Colorado Springs（科罗拉多大学科罗拉多泉分校）；UCCS（科罗拉多泉分校（UCCS））；University of Colorado, Colorado Springs, USA（美国科罗拉多大学科罗拉多泉分校）；Colorado Springs, USA（美国科罗拉多泉）
Deep neural networks provide state-of-the-art performance on various tasks and are, therefore, widely used in real world applications. DNNs are becoming frequently utilized in biometrics for extracting deep features, which can be used in recognition systems for enrolling and recognizing new individuals. It was revealed that deep neural networks suffer from a fundamental problem, namely, they can unexpectedly misclassify examples formed by slightly perturbing correctly recognized inputs. Various approaches have been developed for generating these so-called adversarial examples, but they aim at …
Berkshire School（伯克希尔学校）；GE Global Research Center（通用电气全球研究中心）
Adversarial noises are useful tools to probe the weakness of deep learning based computer vision algorithms. In this paper, we describe a robust adversarial perturbation (R-AP) method to attack deep proposal-based object detectors and instance segmentation algorithms. Our method focuses on attacking the common component in these algorithms, namely Region Proposal Network (RPN), to universally degrade their performance in a black-box fashion. To do so, we design a loss function that combines a label loss and a novel shape loss, and optimize it with respect to image using a gradient based iterat…
Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Johns Hopkins University（约翰斯·霍普金斯大学）；JD Explore Academy（京东探索研究院）；The University of Sydney（悉尼大学）
Crowd counting, which has been widely adopted for estimating the number of people in safety-critical scenes, is shown to be vulnerable to adversarial examples in the physical world (e.g., adversarial patches). Though harmful, adversarial examples are also valuable for evaluating and better understanding model robustness. However, existing adversarial example generation methods for crowd counting lack strong transferability among different black-box models, which limits their practicability for real-world systems. Motivated by the fact that attacking transferability is positively correlated to …
Jilin University（吉林大学）；Fudan University（复旦大学）；Beihang University（北京航空航天大学）；National University of Singapore（新加坡国立大学）
We study the problem of attacking video recognition models in the black-box setting, where the model information is unknown and the adversary can only make queries to detect the predicted top-1 class and its probability. Compared with the black-box attack on images, attacking videos is more challenging as the computation cost for searching the adversarial perturbations on a video is much higher due to its high dimensionality. To overcome this challenge, we propose a heuristic black-box attack model that generates adversarial perturbations only on the selected frames and regions. More specifica…
Vision Transformers are increasingly embedded in industrial systems due to their superior performance, but their memory and power requirements make deploying them to edge devices a challenging task. Hence, model compression techniques are now widely used to deploy models on edge devices as they decrease the resource requirements and make model inference very fast and efficient. But their reliability and robustness from a security perspective is another major issue in safety-critical applications. Adversarial attacks are like optical illusions for ML algorithms and they can severely impact the …
The output of Convolutional Neural Networks (CNN) has been shown to be discontinuous which can make the CNN image classifier vulnerable to small well-tuned artificial perturbations. That is, images modified by adding such perturbations(i.e. adversarial perturbations) that make little difference to human eyes, can completely alter the CNN classification results. In this paper, we propose a practical attack using differential evolution(DE) for generating effective adversarial perturbations. We comprehensively evaluate the effectiveness of different types of DEs for conducting the attack on diffe…
Recent advances in deep neural networks (DNNs) have significantly enhanced the capabilities of optical character recognition (OCR) technology, enabling its adoption to a wide range of real-world applications. Despite this success, DNN-based OCR is shown to be vulnerable to adversarial attacks, in which the adversary can influence the DNN model's prediction by carefully manipulating input to the model. Prior work has demonstrated the security impacts of adversarial attacks on various OCR languages. However, to date, no studies have been conducted and evaluated on an OCR system tailored specific…
University of Edinburgh（爱丁堡大学）；Samsung AI Center, Cambridge（三星剑桥人工智能中心）
This paper investigates a family of methods for defending against adversarial attacks that owe part of their success to creating a noisy, discontinuous, or otherwise rugged loss landscape that adversaries find difficult to navigate. A common, but not universal, way to achieve this effect is via the use of stochastic neural networks. We show that this is a form of gradient obfuscation, and propose a general extension to gradient-based adversaries based on the Weierstrass transform, which smooths the surface of the loss function and provides more reliable gradient estimates. We further show that…
State-of-the-art deep neural networks (DNNs) have been proved to have excellent performance on unsupervised domain adaption (UDA). However, recent work shows that DNNs perform poorly when being attacked by adversarial samples, where these attacks are implemented by simply adding small disturbances to the original images. Although plenty of work has focused on this, as far as we know, there is no systematic research on the robustness of unsupervised domain adaption model. Hence, we discuss the robustness of unsupervised domain adaption against adversarial attacking for the first time. We benchm…
In recent years, deep learning has shown impressive performance on many tasks. However, recent researches showed that deep learning systems are vulnerable to small, specially crafted perturbations that are imperceptible to humans. Images with such perturbations are the so called adversarial examples, which have proven to be an indisputable threat to the DNN based applications. The lack of better understanding of the DNNs has prevented the development of efficient defenses against adversarial examples. In this paper, we propose a two-stream architecture to protect CNN from attacking by adversar…
A recent line of work on black-box adversarial attacks has revived the use of transfer from surrogate models by integrating it into query-based search. However, we find that existing approaches of this type underperform their potential, and can be overly complicated besides. Here, we provide a short and simple algorithm which achieves state-of-the-art results through a search which uses the surrogate network's class-score gradients, with no need for other priors or heuristics. The guiding assumption of the algorithm is that the studied networks are in a fundamental sense learning similar funct…
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…
Attacking the Loop: Adversarial Attacks on Graph-based Loop Closure Detection
School of Computer Science, University of Auckland（奥克兰大学计算机科学学院）；Institute for Medical Informatics, Statistics and Documentation, Medical University Graz（格拉茨医科大学医学信息学、统计学与文档学研究所）；Callaghan Innovation（卡拉汉创新公司）
Deep learning models are vulnerable to adversarial examples. As a more threatening type for practical deep learning systems, physical adversarial examples have received extensive research attention in recent years. However, without exploiting the intrinsic characteristics such as model-agnostic and human-specific patterns, existing works generate weak adversarial perturbations in the physical world, which fall short of attacking across different models and show visually suspicious appearance. Motivated by the viewpoint that attention reflects the intrinsic characteristics of the recognition pr…
Anhui University（安徽大学）；Anqing Normal University（安庆师范大学）
Fooling deep neural networks (DNNs) with the black-box optimization has become a popular adversarial attack fashion, as the structural prior knowledge of DNNs is always unknown. Nevertheless, recent black-box adversarial attacks may struggle to balance their attack ability and visual quality of the generated adversarial examples (AEs) in tackling high-resolution images. In this paper, we propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA. By considering the spatial semantic information of images, we firstly…
TEHTRIS；National Institute of Informatics（国立情报学研究所）；The Graduate University for Advanced Studies, SOKENDAI（综合研究大学院大学）；University of Tokyo（东京大学）
This paper presents the first adversarial example based method for attacking human instance segmentation networks, namely person segmentation networks in short, which are harder to fool than classification networks. We propose a novel Fashion-Guided Adversarial Attack (FashionAdv) framework to automatically identify attackable regions in the target image to minimize the effect on image quality. It generates adversarial textures learned from fashion style images and then overlays them on the clothing regions in the original image to make all persons in the image invisible to person segmentation…
Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction
State Key Laboratory of Complex & Critical Software Environment (CCSE), Beihang University（复杂与关键软件环境国家重点实验室，北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；Department of Information Technology and Electrical Engineering, ETH Zurich（苏黎世联邦理工学院信息科技与电气工程系）
University of California, Riverside（加州大学河滨分校）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Tencent（腾讯）
A hard challenge in developing practical face recognition (FR) attacks is due to the black-box nature of the target FR model, i.e., inaccessible gradient and parameter information to attackers. While recent research took an important step towards attacking black-box FR models through leveraging transferability, their performance is still limited, especially against online commercial FR systems that can be pessimistic (e.g., a less than 50% ASR--attack success rate on average). Motivated by this, we present Sibling-Attack, a new FR attack technique for the first time explores a novel multi-task…
Deep learning models have shown their vulnerability when dealing with adversarial attacks. Existing attacks almost perform on low-level instances, such as pixels and super-pixels, and rarely exploit semantic clues. For face recognition attacks, existing methods typically generate the l_p-norm perturbations on pixels, however, resulting in low attack transferability and high vulnerability to denoising defense models. In this work, instead of performing perturbations on the low-level pixels, we propose to generate attacks through perturbing on the high-level semantics to improve attack transfera…
This paper aims to explain adversarial attacks in terms of how adversarial perturbations contribute to the attacking task. We estimate attributions of different image regions to the decrease of the attacking cost based on the Shapley value. We define and quantify interactions among adversarial perturbation pixels, and decompose the entire perturbation map into relatively independent perturbation components. The decomposition of the perturbation map shows that adversarially-trained DNNs have more perturbation components in the foreground than normally-trained DNNs. Moreover, compared to the nor…
University of Michigan Ann Arbor（密歇根大学安娜堡分校）；University of Washington（华盛顿大学）；University of California, Berkeley（加州大学伯克利分校）；Stony Brook University（石溪大学）；Stanford University（斯坦福大学）
Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversarial inputs are created such that, when provided to a deep learning algorithm, they are very likely to be mislabeled. This can be problematic when deep learning is used to assist in safety critical decisions. Recent research has shown that classifiers can be attacked by physical adversarial examples under various physical conditions. Given the fact that state-of-the-art objectio…
University of Electronic Science and Technology of China（电子科技大学）；Beihang University（北京航空航天大学）；Hunan University（湖南大学）
For black-box attacks, the gap between the substitute model and the victim model is usually large, which manifests as a weak attack performance. Motivated by the observation that the transferability of adversarial examples can be improved by attacking diverse models simultaneously, model augmentation methods which simulate different models by using transformed images are proposed. However, existing transformations for spatial domain do not translate to significantly diverse augmented models. To tackle this issue, we propose a novel spectrum simulation attack to craft more transferable adversar…
Adversarial attacks against deep learning-based object detectors (ODs) have been studied extensively in the past few years. These attacks cause the model to make incorrect predictions by placing a patch containing an adversarial pattern on the target object or anywhere within the frame. However, none of prior research proposed a misclassification attack on ODs, in which the patch is applied on the target object. In this study, we propose a novel, universal, targeted, label-switch attack against the state-of-the-art object detector, YOLO. In our attack, we use (i) a tailored projection function…
