Recently, the vulnerability of deep image classification models to adversarial attacks has been investigated. However, such an issue has not been thoroughly studied for image-to-image tasks that take an input image and generate an output image (e.g., colorization, denoising, deblurring, etc.) This paper presents comprehensive investigations into the vulnerability of deep image-to-image models to adversarial attacks. For five popular image-to-image tasks, 16 deep models are analyzed from various standpoints such as output quality degradation due to attacks, transferability of adversarial examples across different tasks, and characteristics of perturbations. We show that unlike image classification tasks, the performance degradation on image-to-image tasks largely differs depending on various factors, e.g., attack methods and task objectives. In addition, we analyze the effectiveness of conventional defense methods used for classification models in improving the robustness of the image-to-image models.
Ti-Patch: Tiled Physical Adversarial Patch for no-reference video quality metrics
Lomonosov Moscow State University（莫斯科罗蒙诺索夫国立大学）；ISP RAS Research Center for Trusted Artificial Intelligence（俄罗斯科学院系统编程研究所可信人工智能研究中心）；Ivannikov Institute for System Programming of the RAS（俄罗斯科学院伊万尼科夫系统编程研究所）；MSU Institute for Artificial Intelligence（莫斯科国立大学人工智能学院）
Convolutional neural networks (CNN) have been more and more applied in mobile robotics such as intelligent vehicles. Security of CNNs in robotics applications is an important issue, for which potential adversarial attacks on CNNs are worth research. Pooling is a typical step of dimension reduction and information discarding in CNNs. Such information discarding may result in mis-deletion and mis-preservation of data features which largely influence the output of the network. This may aggravate the vulnerability of CNNs to adversarial attacks. In this paper, we conduct adversarial attacks on CNN…
Recent advances in video manipulation techniques have made the generation of fake videos more accessible than ever before. Manipulated videos can fuel disinformation and reduce trust in media. Therefore detection of fake videos has garnered immense interest in academia and industry. Recently developed Deepfake detection methods rely on deep neural networks (DNNs) to distinguish AI-generated fake videos from real videos. In this work, we demonstrate that it is possible to bypass such detectors by adversarially modifying fake videos synthesized using existing Deepfake generation methods. We furt…
Simon Fraser University（西蒙弗雷泽大学）；Indian Institute of Technology, Guwahati（印度理工学院古瓦哈提分校）
Recently, there have been several successful deep learning approaches for automatically classifying chest X-ray images into different disease categories. However, there is not yet a comprehensive vulnerability analysis of these models against the so-called adversarial perturbations/attacks, which makes deep models more trustful in clinical practices. In this paper, we extensively analyzed the performance of two state-of-the-art classification deep networks on chest X-ray images. These two networks were attacked by three different categories (ten methods in total) of adversarial methods (both w…
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to use the methodology of adversarial training. We analyze the adversarially trained robust models to study their vulnerability against adversarial attacks at the level of the latent layers. Our analysis reveals that contrary to the input layer which is robust to adversarial attack, the latent layer of these robust models are highly susceptible to adversarial …
Appearance-based gaze estimation has achieved significant improvement by using deep learning. However, many deep learning-based methods suffer from the vulnerability property, i.e., perturbing the raw image using noise confuses the gaze estimation models. Although the perturbed image visually looks similar to the original image, the gaze estimation models output the wrong gaze direction. In this paper, we investigate the vulnerability of appearance-based gaze estimation. To our knowledge, this is the first time that the vulnerability of gaze estimation to be found. We systematically characteri…
Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks. Currently, there is no clear insight into how slight perturbations cause such a large difference in classification results and how we can design a more robust model architecture. In this work, we propose a novel interpretability method, InterpretGAN, to generate explanations for features used for classification in latent variables. Interpreting the classification process of adversarial examples exposes how adversarial perturbations influence features layer by layer as well as which features are modified by perturbat…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Despite the tremendous success of deep neural networks across various tasks, their vulnerability to imperceptible adversarial perturbations has hindered their deployment in the real world. Recently, works on randomized ensembles have empirically demonstrated significant improvements in adversarial robustness over standard adversarially trained (AT) models with minimal computational overhead, making them a promising solution for safety-critical resource-constrained applications. However, this impressive performance raises the question: Are these robustness gains provided by randomized ensembles…
Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense against such adversarial attacks. This work focuses on improving adversarial training to boost adversarial robustness. We first analyze, from an instance-wise perspective, how adversarial vulnerability evolves during adversarial training. We find that during training an overall reduction of adversarial loss is achieved by sacrificing a considerable proporti…
Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR
College of Electronic Science and Technology, National University of Defense Technology（国防科技大学电子科学学院）；Test Center, National University of Defense Technology（国防科技大学测试中心）
Korea Advanced Institute of Science Technology (KAIST)（韩国科学技术院）
Batch normalization (BN) has been widely used in modern deep neural networks (DNNs) due to improved convergence. BN is observed to increase the model accuracy while at the cost of adversarial robustness. There is an increasing interest in the ML community to understand the impact of BN on DNNs, especially related to the model robustness. This work attempts to understand the impact of BN on DNNs from a non-robust feature perspective. Straightforwardly, the improved accuracy can be attributed to the better utilization of useful features. It remains unclear whether BN mainly favors learning robus…
Deep Learning is able to solve a plethora of once impossible problems. However, they are vulnerable to input adversarial attacks preventing them from being autonomously deployed in critical applications. Several algorithm-centered works have discussed methods to cause adversarial attacks and improve adversarial robustness of a Deep Neural Network (DNN). In this work, we elicit the advantages and vulnerabilities of hybrid 6T-8T memories to improve the adversarial robustness and cause adversarial attacks on DNNs. We show that bit-error noise in hybrid memories due to erroneous 6T-SRAM cells have…
University of California, Davis（加州大学戴维斯分校）；Visa Research（Visa研究院）；Linköping University（林雪平大学）
Adversarial attacks on a convolutional neural network (CNN) -- injecting human-imperceptible perturbations into an input image -- could fool a high-performance CNN into making incorrect predictions. The success of adversarial attacks raises serious concerns about the robustness of CNNs, and prevents them from being used in safety-critical applications, such as medical diagnosis and autonomous driving. Our work introduces a visual analytics approach to understanding adversarial attacks by answering two questions: (1) which neurons are more vulnerable to attacks and (2) which image features do t…
Deep neural networks (DNNs) for medical images are extremely vulnerable to adversarial examples (AEs), which poses security concerns on clinical decision making. Luckily, medical AEs are also easy to detect in hierarchical feature space per our study herein. To better understand this phenomenon, we thoroughly investigate the intrinsic characteristic of medical AEs in feature space, providing both empirical evidence and theoretical explanations for the question: why are medical adversarial attacks easy to detect? We first perform a stress test to reveal the vulnerability of deep representations…
Vector Institute（向量研究所）；University of Toronto（多伦多大学）；University of Bremen（不来梅大学）；Center for Industrial Mathematics（工业数学中心）；University of Tübingen（图宾根大学）
Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs. One core idea of adversarial example research is to reveal neural network errors under such distribution shifts. We decompose these errors into two complementary sources: sensitivity and invariance. We show deep networks are not only too sensitive to task-irrelevant changes of their input, as is well-known from epsilon-adversarial examples, but are also too invariant to a wide range of task-relevant changes, thus making vast regions in input space vulnerable to adversarial attack…
University of Oxford（牛津大学）；FiveAI Ltd.（FiveAI有限公司）
The vulnerability of deep image classification networks to adversarial attack is now well known, but less well understood. Via a novel experimental analysis, we illustrate some facts about deep convolutional networks for image classification that shed new light on their behaviour and how it connects to the problem of adversaries. In short, the celebrated performance of these networks and their vulnerability to adversarial attack are simply two sides of the same coin: the input image-space directions along which the networks are most vulnerable to attack are the same directions which they use t…
Under the epidemic of the novel coronavirus disease 2019 (COVID-19), chest X-ray computed tomography imaging is being used for effectively screening COVID-19 patients. The development of computer-aided systems based on deep neural networks (DNNs) has been advanced, to rapidly and accurately detect COVID-19 cases, because the need for expert radiologists, who are limited in number, forms a bottleneck for the screening. However, so far, the vulnerability of DNN-based systems has been poorly evaluated, although DNNs are vulnerable to a single perturbation, called universal adversarial perturbatio…
Deep neural networks are susceptible to small-but-specific adversarial perturbations capable of deceiving the network. This vulnerability can lead to potentially harmful consequences in security-critical applications. To address this vulnerability, we propose a novel metric called \emph{Gradient Similarity} that allows us to capture the influence of training data on test inputs. We show that \emph{Gradient Similarity} behaves differently for normal and adversarial inputs, and enables us to detect a variety of adversarial attacks with a near perfect ROC-AUC of 95-100\%. Even white-box adversari…
Recently, Convolutional Neural Networks (CNNs) demonstrate a considerable vulnerability to adversarial attacks, which can be easily misled by adversarial perturbations. With more aggressive methods proposed, adversarial attacks can be also applied to the physical world, causing practical issues to various CNN powered applications. To secure CNNs, adversarial attack detection is considered as the most critical approach. However, most existing works focus on superficial patterns and merely search a particular method to differentiate the adversarial inputs and natural inputs, ignoring the analysi…
University of California, Davis（加利福尼亚大学戴维斯分校）；NEC Laboratories America（NEC美国实验室）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Recent studies have demonstrated the vulnerability of deep convolutional neural networks against adversarial examples. Inspired by the observation that the intrinsic dimension of image data is much smaller than its pixel space dimension and the vulnerability of neural networks grows with the input dimension, we propose to embed high-dimensional input images into a low-dimensional space to perform classification. However, arbitrarily projecting the input images to a low-dimensional space without regularization will not improve the robustness of deep neural networks. Leveraging optimal transport…
Recently, adversarial attacks can be applied to the physical world, causing practical issues to various Convolutional Neural Networks (CNNs) powered applications. Most existing physical adversarial attack defense works only focus on eliminating explicit perturbation patterns from inputs, ignoring interpretation to CNN's intrinsic vulnerability. Therefore, they lack the expected versatility to different attacks and thereby depend on considerable data processing costs. In this paper, we propose LanCe -- a comprehensive and lightweight CNN defense methodology against different physical adversaria…
Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular importance. An appropriate solution to adversarial attacks is adversarial training, which reaches a trade-off between robustness and generalization. This paper introduces a novel framework (Layer Sustainability Analysis (LSA)) for the analysis of layer vulnerability in an arbitrary neural network in the scenario of adversarial attacks. LSA can be a helpful toolkit to assess deep neural networks and to extend the adversaria…
The adversarial vulnerability of deep neural networks (DNNs) has been actively investigated in the past several years. This paper investigates the scale-variant property of cross-entropy loss, which is the most commonly used loss function in classification tasks, and its impact on the effective margin and adversarial robustness of deep neural networks. Since the loss function is not invariant to logit scaling, increasing the effective weight norm will make the loss approach zero and its gradient vanish while the effective margin is not adequately maximized. On typical DNNs, we demonstrate that…
The Chinese University of Hong Kong（香港中文大学）；Nanyang Technological University（南洋理工大学）；Huawei（华为）；Tsinghua University（清华大学）；SenseTime-CUHK Joint Lab（商汤科技-香港中文大学联合实验室）；Centre of Perceptual and Interactive Intelligence（感知与交互智能中心）；Shanghai AI Laboratory（上海人工智能实验室）
Adversarial robustness has attracted extensive studies recently by revealing the vulnerability and intrinsic characteristics of deep networks. However, existing works on adversarial robustness mainly focus on balanced datasets, while real-world data usually exhibits a long-tailed distribution. To push adversarial robustness towards more realistic scenarios, in this work we investigate the adversarial vulnerability as well as defense under long-tailed distributions. In particular, we first reveal the negative impacts induced by imbalanced data on both recognition performance and adversarial rob…
According to recent studies, the vulnerability of state-of-the-art Neural Networks to adversarial input samples has increased drastically. A neural network is an intermediate path or technique by which a computer learns to perform tasks using Machine learning algorithms. Machine Learning and Artificial Intelligence model has become a fundamental aspect of life, such as self-driving cars [1], smart home devices, so any vulnerability is a significant concern. The smallest input deviations can fool these extremely literal systems and deceive their users as well as administrator into precarious si…
We evaluate the robustness of Adversarial Logit Pairing, a recently proposed defense against adversarial examples. We find that a network trained with Adversarial Logit Pairing achieves 0.6% accuracy in the threat model in which the defense is considered. We provide a brief overview of the defense and the threat models/claims considered, as well as a discussion of the methodology and results of our attack, which may offer insights into the reasons underlying the vulnerability of ALP to adversarial attack.
Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical applications. In this paper, we conjecture that the leading cause of adversarial vulnerability is the distortion in the latent feature space, and provide methods to suppress them effectively. Explicitly, we define \emph{vulnerability} for each latent feature and then propose a new loss for adversarial learning, \emph{Vulnerability Suppression (VS)} loss, that aims to mi…
The success of multimodal data fusion in deep learning appears to be attributed to the use of complementary in-formation between multiple input data. Compared to their predictive performance, relatively less attention has been devoted to the robustness of multimodal fusion models. In this paper, we investigated whether the current multimodal fusion model utilizes the complementary intelligence to defend against adversarial attacks. We applied gradient based white-box attacks such as FGSM and PGD on MFNet, which is a major multispectral (RGB, Thermal) fusion deep learning model for semantic seg…
Facebook AI Research（Facebook人工智能研究院）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Over the past few years, neural networks were proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions. We show that adversarial vulnerability increases with the gradients of the training objective when viewed as a function of the inputs. Surprisingly, vulnerability does not depend on network topology: for many standard network architectures, we prove that at initialization, the $\ell_1$-norm of these gradients grows as the square root of the input dimension, leaving the networks increasingly vulnerable with growing image…
Univ Lyon（里昂大学）；ENS de Lyon（里昂高等师范学院）；CNRS（法国国家科学研究中心）；UCBL（里昂第一大学）；DeepMind（深度思维）；University of Cambridge（剑桥大学）
Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we study the phenomenon of adversarial perturbations under the assumption that the data is generated with a smooth generative model. We derive fundamental upper bounds on the robustness to perturbations of any classification function, and prove the existence of adversarial perturbations that transfer well across different classifiers with small risk. Our analy…
University of Toronto（多伦多大学）；State University of New York at Buffalo（纽约州立大学布法罗分校）；Zhejiang University（浙江大学）
Skeleton-based action recognition has attracted increasing attention due to its strong adaptability to dynamic circumstances and potential for broad applications such as autonomous and anonymous surveillance. With the help of deep learning techniques, it has also witnessed substantial progress and currently achieved around 90\% accuracy in benign environment. On the other hand, research on the vulnerability of skeleton-based action recognition under different adversarial settings remains scant, which may raise security concerns about deploying such techniques into real-world systems. However, …
Erasmus MC（伊拉斯谟医学中心）；Radboudumc（拉德堡德大学医学中心）；Donders Institute for Brain, Cognition and Behaviour（唐德斯大脑、认知与行为研究所）；Eindhoven University of Technology（埃因霍温理工大学）；Intel Corporation（英特尔公司）
Adversarial attacks are considered a potentially serious security threat for machine learning systems. Medical image analysis (MedIA) systems have recently been argued to be vulnerable to adversarial attacks due to strong financial incentives and the associated technological infrastructure. In this paper, we study previously unexplored factors affecting adversarial attack vulnerability of deep learning MedIA systems in three medical domains: ophthalmology, radiology, and pathology. We focus on adversarial black-box settings, in which the attacker does not have full access to the target model a…
Technische Universität Braunschweig（布伦瑞克工业大学）；Volkswagen Group Automation（大众汽车集团自动驾驶部门）
Enabling autonomous driving (AD) can be considered one of the biggest challenges in today's technology. AD is a complex task accomplished by several functionalities, with environment perception being one of its core functions. Environment perception is usually performed by combining the semantic information captured by several sensors, i.e., lidar or camera. The semantic information from the respective sensor can be extracted by using convolutional neural networks (CNNs) for dense prediction. In the past, CNNs constantly showed state-of-the-art performance on several vision-related tasks, such…
Adversarial Vulnerability Transcends Computational Paradigms: Feature Engineering Provides No Defense Against Neural Adversarial Transfer
1 Department of Information \& Computer Science, KFUPM, Dhahran, Saudi Arabia；2 Department of Computer Engineering, KFUPM, Dhahran, Saudi Arabia；3 Interdisciplinary Research Center for Finance
Morphing attacks is a threat to biometric systems where the biometric reference in an identity document can be altered. This form of attack presents an important issue in applications relying on identity documents such as border security or access control. Research in face morphing attack detection is developing rapidly, however very few datasets with several forms of attacks are publicly available. This paper bridges this gap by providing a new dataset with four different types of morphing attacks, based on OpenCV, FaceMorpher, WebMorph and a generative adversarial network (StyleGAN), generat…
With further development in the fields of computer vision, network security, natural language processing and so on so forth, deep learning technology gradually exposed certain security risks. The existing deep learning algorithms cannot effectively describe the essential characteristics of data, making the algorithm unable to give the correct result in the face of malicious input. Based on current security threats faced by deep learning, this paper introduces the problem of adversarial examples in deep learning, sorts out the existing attack and defense methods of the black box and white box, …
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）；University College London（伦敦大学学院）；Zhejiang University（浙江大学）；University of Bath（巴斯大学）；School of Computing, University of Leeds（利兹大学计算学院）
University of Oxford（牛津大学）；Bosch Center for Artificial Intelligence（博世人工智能中心）；University of Freiburg（弗赖堡大学）
Neural architectures based on attention such as vision transformers are revolutionizing image recognition. Their main benefit is that attention allows reasoning about all parts of a scene jointly. In this paper, we show how the global reasoning of (scaled) dot-product attention can be the source of a major vulnerability when confronted with adversarial patch attacks. We provide a theoretical understanding of this vulnerability and relate it to an adversary's ability to misdirect the attention of all queries to a single key token under the control of the adversarial patch. We propose novel adve…
FZI Research Center for Information Technology（FZI信息技术研究中心）；Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院（KIT））
Taking into account information across the temporal domain helps to improve environment perception in autonomous driving. However, it has not been studied so far whether temporally fused neural networks are vulnerable to deliberately generated perturbations, i.e. adversarial attacks, or whether temporal history is an inherent defense against them. In this work, we study whether temporal feature networks for object detection are vulnerable to universal adversarial attacks. We evaluate attacks of two types: imperceptible noise for the whole image and locally-bound adversarial patch. In both case…
Visual detection is a key task in autonomous driving, and it serves as a crucial foundation for self-driving planning and control. Deep neural networks have achieved promising results in various visual tasks, but they are known to be vulnerable to adversarial attacks. A comprehensive understanding of deep visual detectors' vulnerability is required before people can improve their robustness. However, only a few adversarial attack/defense works have focused on object detection, and most of them employed only classification and/or localization losses, ignoring the objectness aspect. In this pape…
Adversarial attack perturbs an image with an imperceptible noise, leading to incorrect model prediction. Recently, a few works showed inherent bias associated with such attack (robustness bias), where certain subgroups in a dataset (e.g. based on class, gender, etc.) are less robust than others. This bias not only persists even after adversarial training, but often results in severe performance discrepancies across these subgroups. Existing works characterize the subgroup's robustness bias by only checking individual sample's proximity to the decision boundary. In this work, we argue that this…
Deep neural networks are susceptible to adversarial manipulations in the input domain. The extent of vulnerability has been explored intensively in cases of $\ell_p$-bounded and $\ell_p$-minimal adversarial perturbations. However, the vulnerability of DNNs to adversarial perturbations with specific statistical properties or frequency-domain characteristics has not been sufficiently explored. In this paper, we study the smoothness of perturbations and propose SmoothFool, a general and computationally efficient framework for computing smooth adversarial perturbations. Through extensive experimen…
The video-based action recognition task has been extensively studied in recent years. In this paper, we study the structural vulnerability of deep learning-based action recognition models against the adversarial attack using the one frame attack that adds an inconspicuous perturbation to only a single frame of a given video clip. Our analysis shows that the models are highly vulnerable against the one frame attack due to their structural properties. Experiments demonstrate high fooling rates and inconspicuous characteristics of the attack. Furthermore, we show that strong universal one frame p…
Investigating and unmasking feature-level vulnerabilities of CNNs to adversarial perturbations
Bioinformatics Institute (BII), Agency for Science, Technology and Research (A*STAR)（生物信息学研究所（BII），科技研究局（A*STAR））；School of Computing, National University of Singapore（新加坡国立大学计算机学院）；School of Biological Sciences, Nanyang Technological University（南洋理工大学生物科学学院）；Singapore Eye Research Institute (SERI)（新加坡眼科研究所（SERI））；Singapore Institute for Clinical Sciences（新加坡临床科学研究院）
