Interpreting neural network classifiers using gradient-based saliency maps has been extensively studied in the deep learning literature. While the existing algorithms manage to achieve satisfactory performance in application to standard image recognition datasets, recent works demonstrate the vulnerability of widely-used gradient-based interpretation schemes to norm-bounded perturbations adversarially designed for every individual input sample. However, such adversarial perturbations are commonly designed using the knowledge of an input sample, and hence perform sub-optimally in application to an unknown or constantly changing data point. In this paper, we show the existence of a Universal Perturbation for Interpretation (UPI) for standard image datasets, which can alter a gradient-based feature map of neural networks over a significant fraction of test samples. To design such a UPI, we propose a gradient-based optimization method as well as a principal component analysis (PCA)-based approach to compute a UPI which can effectively alter a neural network's gradient-based interpretation on different samples. We support the proposed UPI approaches by presenting several numerical results of their successful applications to standard image datasets.
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心 (DFKI)）；TU Kaiserslautern（凯泽斯劳滕工业大学）；NVIDIA Research（英伟达研究院）
In this paper, we investigate the use of pretraining with adversarial networks, with the objective of discovering the relationship between network depth and robustness. For this purpose, we selectively retrain different portions of VGG and ResNet architectures on CIFAR-10, Imagenette, and ImageNet using non-adversarial and adversarial data. Experimental results show that susceptibility to adversarial samples is associated with low-level feature extraction layers. Therefore, retraining of high-level layers is insufficient for achieving robustness. Furthermore, adversarial attacks yield outputs …
Texas A&M University（得克萨斯农工大学）；Arizona State University（亚利桑那州立大学）
Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. Attackers add carefully-crafted perturbations to input, where the perturbations are almost imperceptible to humans, but can cause models to make wrong predictions. Techniques to protect models against adversarial input are called adversarial defense methods. Although many approaches have been proposed to study adversarial attacks and defenses in different scenarios, an intriguing and crucial challenge remains that how…
Tsinghua University（清华大学）；Microsoft Research Asia（微软亚洲研究院）；TTIC（丰田工业大学芝加哥分校）
We consider universal adversarial patches for faces -- small visual elements whose addition to a face image reliably destroys the performance of face detectors. Unlike previous work that mostly focused on the algorithmic design of adversarial examples in terms of improving the success rate as an attacker, in this work we show an interpretation of such patches that can prevent the state-of-the-art face detectors from detecting the real faces. We investigate a phenomenon: patches designed to suppress real face detection appear face-like. This phenomenon holds generally across different initializ…
Washington University in St. Louis（圣路易斯华盛顿大学）；University of Massachusetts at Amherst（马萨诸塞大学阿默斯特分校）
Modern AI tools, such as generative adversarial networks, have transformed our ability to create and modify visual data with photorealistic results. However, one of the deleterious side-effects of these advances is the emergence of nefarious uses in manipulating information in visual data, such as through the use of deep fakes. We propose a novel architecture for preserving the provenance of semantic information in images to make them less susceptible to deep fake attacks. Our architecture includes semantic signing and verification steps. We apply this architecture to verifying two types of se…
This paper provides a unified view to explain different adversarial attacks and defense methods, i.e. the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that adversarial attacks mainly affect high-order interactions to fool the DNN. Furthermore, we find that the robustness of adversarially trained DNNs comes from category-specific low-order interactions. Our findings provide a potential method to unify adversarial perturbations and robustness, which can explain the existing defense methods in a principle way. Besides, our fin…
Deep convolutional neural networks are susceptible to adversarial attacks. They can be easily deceived to give an incorrect output by adding a tiny perturbation to the input. This presents a great challenge in making CNNs robust against such attacks. An influx of new defense techniques have been proposed to this end. In this paper, we show that latent features in certain "robust" models are surprisingly susceptible to adversarial attacks. On top of this, we introduce a unified $\ell_\infty$-norm white-box attack algorithm which harnesses latent features in its gradient descent steps, namely LA…
This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i.e.} the view of multi-order interactions between input variables of DNNs. Based on the multi-order interaction, we discover that adversarial attacks mainly affect high-order interactions to fool the DNN. Furthermore, we find that the robustness of adversarially trained DNNs comes from category-specific low-order interactions. Our findings provide a potential method to unify adversarial perturbations and robustness, which can explain the existing defense methods in a principle way. Besides, …
Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
Department of Computer Science and Engineering, Sungkyunkwan University（计算机科学与工程系，全州大学）；Department of Computer Science, Loyola University（计算机科学系，洛伊拉大学）
Deep learning methods have gained increased attention in various applications due to their outstanding performance. For exploring how this high performance relates to the proper use of data artifacts and the accurate problem formulation of a given task, interpretation models have become a crucial component in developing deep learning-based systems. Interpretation models enable the understanding of the inner workings of deep learning models and offer a sense of security in detecting the misuse of artifacts in the input data. Similar to prediction models, interpretation models are also susceptib…
School of Computing and Information Systems（计算与信息系统学院）；The University of Melbourne（墨尔本大学）
Deep learning classifiers are susceptible to well-crafted, imperceptible variations of their inputs, known as adversarial attacks. In this regard, the study of powerful attack models sheds light on the sources of vulnerability in these classifiers, hopefully leading to more robust ones. In this paper, we introduce AdvFlow: a novel black-box adversarial attack method on image classifiers that exploits the power of normalizing flows to model the density of adversarial examples around a given target image. We see that the proposed method generates adversaries that closely follow the clean data di…
Convolutional neural network-based medical image classifiers have been shown to be especially susceptible to adversarial examples. Such instabilities are likely to be unacceptable in the future of automated diagnoses. Though statistical adversarial example detection methods have proven to be effective defense mechanisms, additional research is necessary that investigates the fundamental vulnerabilities of deep-learning-based systems and how best to build models that jointly maximize traditional and robust accuracy. This paper presents the inclusion of attention mechanisms in CNN-based medical …
Adversarial images are created with the intention of causing an image classifier to produce a misclassification. In this paper, we propose that adversarial images should be evaluated based on semantic mismatch, rather than label mismatch, as used in current work. In other words, we propose that an image of a "mug" would be considered adversarial if classified as "turnip", but not as "cup", as current systems would assume. Our novel idea of taking semantic misclassification into account in the evaluation of adversarial images offers two benefits. First, it is a more realistic conceptualization …
Despite their unmatched performance, deep neural networks remain susceptible to targeted attacks by nearly imperceptible levels of adversarial noise. While the underlying cause of this sensitivity is not well understood, theoretical analyses can be simplified by reframing each layer of a feed-forward network as an approximate solution to a sparse coding problem. Iterative solutions using basis pursuit are theoretically more stable and have improved adversarial robustness. However, cascading layer-wise pursuit implementations suffer from error accumulation in deeper networks. In contrast, our n…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；Mayachitra Inc（玛雅奇特拉公司）
Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment. Automatic reverse engineering of the toolchains behind these adversarial machine learning attacks will aid in recovering the tools and processes used in these attacks. In this paper, we present two techniques that support automated identification and attribution of adversarial ML attack toolchains using Co-occurrence Pixel statistics and Laplacian Residuals. Our experiments show that the proposed techniques can identify parameters used to generate adversarial samples. To t…
It is broadly known that deep neural networks are susceptible to being fooled by adversarial examples with perturbations imperceptible by humans. Various defenses have been proposed to improve adversarial robustness, among which adversarial training methods are most effective. However, most of these methods treat the training samples independently and demand a tremendous amount of samples to train a robust network, while ignoring the latent structural information among these samples. In this work, we propose a novel Local Structure Preserving (LSP) regularization, which aims to preserve the lo…
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…
Intriguing Frequency Interpretation of Adversarial Robustness for CNNs and ViTs
Shanghai Jiao Tong University, China（上海交通大学）；Southeast University, China（东南大学）；Mohamed bin Zayed University of Artificial Intelligence, UAE（穆罕默德·本·扎耶德人工智能大学）；National University of Singapore, Singapore（新加坡国立大学）
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…
Towards the first adversarially robust neural network model on MNIST
Centre for Integrative Neuroscience, University of Tübingen（图宾根大学综合神经科学中心）；Bernstein Center for Computational Neuroscience Tübingen（图宾根伯恩斯坦计算神经科学中心）；International Max Planck Research School for Intelligent Systems（国际马克斯·普朗克智能系统研究学院）；Max Planck Institute for Biological Cybernetics（马克斯·普朗克生物控制论研究所）
Machine Learning has been applied in a wide range of tasks throughout the last years, ranging from image classification to autonomous driving and natural language processing. Restricted Boltzmann Machine (RBM) has received recent attention and relies on an energy-based structure to model data probability distributions. Notwithstanding, such a technique is susceptible to adversarial manipulation, i.e., slightly or profoundly modified data. An alternative to overcome the adversarial problem lies in the Generative Adversarial Networks (GAN), capable of modeling data distributions and generating a…
Triggering hallucinations in model-based MRI reconstruction via adversarial perturbations
Faculty of Engineering and Architecture/Computer Engineering（工程与建筑学院/计算机工程学院）；Department of Computer Science, Mathematics and Statistics（计算机科学、数学与统计学系）；Ghent University（根特大学）；Data Mining and Modeling for Biomedicine Group（生物医学数据挖掘与建模小组）；VIB Inflammation Research Center（VIB炎症研究中心）
Monash University（莫纳什大学）；Defence Science and Technology Group（国防科技集团）
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges as the most successful method that consistently resists a wide range of attacks. In this work, based on an observation from a previous study that the representations of a clean data example and its adversarial examples become more divergent in higher layers of a deep neural net, we propose the Adversary Divergence Reduction Network which enforces local/globa…
Previous studies have demonstrated that commonly studied (vanilla) touch-based continuous authentication systems (V-TCAS) are susceptible to population attack. This paper proposes a novel Generative Adversarial Network assisted TCAS (G-TCAS) framework, which showed more resilience to the population attack. G-TCAS framework was tested on a dataset of 117 users who interacted with a smartphone and tablet pair. On average, the increase in the false accept rates (FARs) for V-TCAS was much higher (22%) than G-TCAS (13%) for the smartphone. Likewise, the increase in the FARs for V-TCAS was 25% compa…
Institute of Information Science（信息科学研究所）；Beijing Jiaotong University（北京交通大学）
Recent studies have shown that deep neural networks are vulnerable to adversarial examples, but most of the methods proposed to defense adversarial examples cannot solve this problem fundamentally. In this paper, we theoretically prove that there is an upper bound for neural networks with identity mappings to constrain the error caused by adversarial noises. However, in actual computations, this kind of neural network no longer holds any upper bound and is therefore susceptible to adversarial examples. Following similar procedures, we explain why adversarial examples can fool other deep neural…
University of Göttingen（哥廷根大学）；neurocat GmbH（neurocat有限公司）
Machine learning image classifiers are susceptible to adversarial and corruption perturbations. Adding imperceptible noise to images can lead to severe misclassifications of the machine learning model. Using $L_p$-norms for measuring the size of the noise fails to capture human similarity perception, which is why optimal transport based distance measures like the Wasserstein metric are increasingly being used in the field of adversarial robustness. Verifying the robustness of classifiers using the Wasserstein metric can be achieved by proving the absence of adversarial examples (certification)…
VITAL: A Visual Interpretation on Text with Adversarial Learning for Image Labeling
School of Computer Science, Wuhan University, Wuhan, Hubei, China（中国湖北省武汉市武汉大学计算机学院）；School of Information Engineering, Hubei University for Nationalities, Enshi, Hubei, China（中国湖北省恩施市湖北民族学院信息工程学院）
Yantai University（烟台大学）；East China Normal University（华东师范大学）
Neural networks are susceptible to artificially designed adversarial perturbations. Recent efforts have shown that imposing certain modifications on classification layer can improve the robustness of the neural networks. In this paper, we explicitly construct a dense orthogonal weight matrix whose entries have the same magnitude, thereby leading to a novel robust classifier. The proposed classifier avoids the undesired structural redundancy issue in previous work. Applying this classifier in standard training on clean data is sufficient to ensure the high accuracy and good robustness of the mo…
Current machine learning models achieve super-human performance in many real-world applications. Still, they are susceptible against imperceptible adversarial perturbations. The most effective solution for this problem is adversarial training that trains the model with adversarially perturbed samples instead of original ones. Various methods have been developed over recent years to improve adversarial training such as data augmentation or modifying training attacks. In this work, we examine the same problem from a new data-centric perspective. For this purpose, we first demonstrate that the ex…
Efficient Model-Based Purification Against Adversarial Attacks for LiDAR Segmentation
Industrial Systems Institute, Athena Research Center, Patras Science Park, Greece（工业系统研究所，雅典研究中心，帕特拉斯科学公园，希腊）；AviSense.AI, Patras Science Park, Greece（AviSense.AI，帕特拉斯科学公园，希腊）
Tsinghua University（清华大学）；Guangxi University（广西大学）；Samsung Research China - Beijing (SRC-B)（中国三星研究院北京分院）
Recently, 3D deep learning models have been shown to be susceptible to adversarial attacks like their 2D counterparts. Most of the state-of-the-art (SOTA) 3D adversarial attacks perform perturbation to 3D point clouds. To reproduce these attacks in the physical scenario, a generated adversarial 3D point cloud need to be reconstructed to mesh, which leads to a significant drop in its adversarial effect. In this paper, we propose a strong 3D adversarial attack named Mesh Attack to address this problem by directly performing perturbation on mesh of a 3D object. In order to take advantage of the m…
Deep neural networks have been widely used in many computer vision tasks. However, it is proved that they are susceptible to small, imperceptible perturbations added to the input. Inputs with elaborately designed perturbations that can fool deep learning models are called adversarial examples, and they have drawn great concerns about the safety of deep neural networks. Object detection algorithms are designed to locate and classify objects in images or videos and they are the core of many computer vision tasks, which have great research value and wide applications. In this paper, we focus on a…
