Achieving transferability of targeted attacks is reputed to be remarkably difficult. Currently, state-of-the-art approaches are resource-intensive because they necessitate training model(s) for each target class with additional data. In our investigation, we find, however, that simple transferable attacks which require neither additional data nor model training can achieve surprisingly high targeted transferability. This insight has been overlooked until now, mainly due to the widespread practice of unreasonably restricting attack optimization to a limited number of iterations. In particular, we, for the first time, identify that a simple logit loss can yield competitive results with the state of the arts. Our analysis spans a variety of transfer settings, especially including three new, realistic settings: an ensemble transfer setting with little model similarity, a worse-case setting with low-ranked target classes, and also a real-world attack against the Google Cloud Vision API. Results in these new settings demonstrate that the commonly adopted, easy settings cannot fully reveal the actual properties of different attacks and may cause misleading comparisons. We also show the usefulness of the simple logit loss for generating targeted universal adversarial perturbations in a data-free and training-free manner. Overall, the aim of our analysis is to inspire a more meaningful evaluation on targeted transferability. Code is available at https://github.com/ZhengyuZhao/Targeted-Tansfer
Deep Neural Networks have been found vulnerable re-cently. A kind of well-designed inputs, which called adver-sarial examples, can lead the networks to make incorrectpredictions. Depending on the different scenarios, goalsand capabilities, the difficulties of the attacks are different.For example, a targeted attack is more difficult than a non-targeted attack, a universal attack is more difficult than anon-universal attack, a transferable attack is more difficultthan a nontransferable one. The question is: Is there existan attack that can meet all these requirements? In this pa-per, we answer …
University of Electronic Science and Technology of China（电子科技大学）
In this work, we study the black-box targeted attack problem from the model discrepancy perspective. On the theoretical side, we present a generalization error bound for black-box targeted attacks, which gives a rigorous theoretical analysis for guaranteeing the success of the attack. We reveal that the attack error on a target model mainly depends on empirical attack error on the substitute model and the maximum model discrepancy among substitute models. On the algorithmic side, we derive a new algorithm for black-box targeted attacks based on our theoretical analysis, in which we additionall…
UC Berkeley（加州大学伯克利分校）；Shanghai Jiao Tong University（上海交通大学）；University of the California, Berkeley（加州大学伯克利分校）
An intriguing property of deep neural networks is the existence of adversarial examples, which can transfer among different architectures. These transferable adversarial examples may severely hinder deep neural network-based applications. Previous works mostly study the transferability using small scale datasets. In this work, we are the first to conduct an extensive study of the transferability over large models and a large scale dataset, and we are also the first to study the transferability of targeted adversarial examples with their target labels. We study both non-targeted and targeted ad…
Los Alamos National Laboratory（洛斯阿拉莫斯国家实验室）；Santa Fe Institute（圣塔菲研究所）
Adversarial examples for neural network image classifiers are known to be transferable: examples optimized to be misclassified by a source classifier are often misclassified as well by classifiers with different architectures. However, targeted adversarial examples -- optimized to be classified as a chosen target class -- tend to be less transferable between architectures. While prior research on constructing transferable targeted attacks has focused on improving the optimization procedure, in this work we examine the role of the source classifier. Here, we show that training the source classi…
Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations carefully crafted to fool the targeted DNN, in both the non-targeted and targeted case. In the non-targeted case, the attacker simply aims to induce misclassification. In the targeted case, the attacker aims to induce classification to a specified target class. In addition, it has been observed that strong adversarial examples can transfer to unknown models, yielding a serious security concern. The NIPS 2017 competition was organized to accelerate research in adversarial attacks and defenses, taking place in the …
Malicious attackers can generate targeted adversarial examples by imposing tiny noises, forcing neural networks to produce specific incorrect outputs. With cross-model transferability, network models remain vulnerable even in black-box settings. Recent studies have shown the effectiveness of ensemble-based methods in generating transferable adversarial examples. To further enhance transferability, model augmentation methods aim to produce more networks participating in the ensemble. However, existing model augmentation methods are only proven effective in untargeted attacks. In this work, we p…
Carnegie Mellon University（卡内基梅隆大学）；University of Florida（佛罗里达大学）
A targeted adversarial attack produces audio samples that can force an Automatic Speech Recognition (ASR) system to output attacker-chosen text. To exploit ASR models in real-world, black-box settings, an adversary can leverage the transferability property, i.e. that an adversarial sample produced for a proxy ASR can also fool a different remote ASR. However recent work has shown that transferability against large ASR models is very difficult. In this work, we show that modern ASR architectures, specifically ones based on Self-Supervised Learning, are in fact vulnerable to transferability. We …
University of Maryland, College Park（马里兰大学帕克分校）；United States Naval Academy（美国海军学院）；Cornell University（康奈尔大学）
Clean-label poisoning attacks inject innocuous looking (and "correctly" labeled) poison images into training data, causing a model to misclassify a targeted image after being trained on this data. We consider transferable poisoning attacks that succeed without access to the victim network's outputs, architecture, or (in some cases) training data. To achieve this, we propose a new "polytope attack" in which poison images are designed to surround the targeted image in feature space. We also demonstrate that using Dropout during poison creation helps to enhance transferability of this attack. We …
CuraCloud Corporation（库拉云公司）；University at Albany, State University of New York（纽约州立大学奥尔巴尼分校）；Chengdu University of Information Technology（成都信息工程大学）
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbations can completely change the classification results. Their vulnerability has led to a surge of research in this direction. However, most works dedicated to attacking anchor-based object detection models. In this work, we aim to present an effective and efficient algorithm to generate adversarial examples to attack anchor-free object models based on two approaches. First, we conduct category-wise instead of instance-wise attacks on the object detectors. Second, we leverage the high-level seman…
RaPA: Enhancing Transferable Targeted Attacks via Random Parameter Pruning
State Key Lab of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所人工智能安全国家重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）
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…
Almost all current adversarial attacks of CNN classifiers rely on information derived from the output layer of the network. This work presents a new adversarial attack based on the modeling and exploitation of class-wise and layer-wise deep feature distributions. We achieve state-of-the-art targeted blackbox transfer-based attack results for undefended ImageNet models. Further, we place a priority on explainability and interpretability of the attacking process. Our methodology affords an analysis of how adversarial attacks change the intermediate feature distributions of CNNs, as well as a mea…
The length and time scales of atomistic simulations are limited by the computational cost of the methods used to predict material properties. In recent years there has been great progress in the use of machine learning algorithms to develop fast and accurate interatomic potential models, but it remains a challenge to develop models that generalize well and are fast enough to be used at extreme time and length scales. To address this challenge, we have developed a machine learning algorithm based on symbolic regression in the form of genetic programming that is capable of discovering accurate, …
We study the problem of user association, namely finding the optimal assignment of user equipment to base stations to achieve a targeted network performance. In this paper, we focus on the knowledge transferability of association policies. Indeed, traditional non-trivial user association schemes are often scenario-specific or deployment-specific and require a policy re-design or re-learning when the number or the position of the users change. In contrast, transferability allows to apply a single user association policy, devised for a specific scenario, to other distinct user deployments, witho…
Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
Computer Vision Institute（计算机视觉研究所）；School of Computer Science & Software Engineering（计算机科学与软件工程学院）；Shenzhen University（深圳大学）；Shenzhen Institute of Artificial Intelligence Robotics for Society（深圳人工智能与机器人社会研究院）；Guangdong Provincial Key Laboratory of Intelligent Information Processing（广东省智能信息处理重点实验室）；University of Exeter（埃克塞特大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
The vulnerability of the Lottery Ticket Hypothesis has not been studied from the purview of Membership Inference Attacks. Through this work, we are the first to empirically show that the lottery ticket networks are equally vulnerable to membership inference attacks. A Membership Inference Attack (MIA) is the process of determining whether a data sample belongs to a training set of a trained model or not. Membership Inference Attacks could leak critical information about the training data that can be used for targeted attacks. Recent deep learning models often have very large memory footprints …
AI Foundations Group IBM T. J. Watson Research Center（IBM T. J. Watson 研究中心 AI 基础组）；University of California, Davis（加州大学戴维斯分校）；IBM T. J. Watson Research Center（IBM T. J. Watson 研究中心）
Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image classification, text mining, and speech processing. However, recent research on DNNs has indicated ever-increasing concern on the robustness to adversarial examples, especially for security-critical tasks such as traffic sign identification for autonomous driving. Studies have unveiled the vulnerability of a well-trained DNN by demonstrating the ability of generating barely noticeable (to both human a…
University of California, Santa Barbara（加州大学圣巴巴拉分校）
A recent source of concern for the security of neural networks is the emergence of clean-label dataset poisoning attacks, wherein correctly labeled poison samples are injected into the training dataset. While these poison samples look legitimate to the human observer, they contain malicious characteristics that trigger a targeted misclassification during inference. We propose a scalable and transferable clean-label poisoning attack against transfer learning, which creates poison images with their center close to the target image in the feature space. Our attack, Bullseye Polytope, improves the…
Blackbox adversarial attacks can be categorized into transfer- and query-based attacks. Transfer methods do not require any feedback from the victim model, but provide lower success rates compared to query-based methods. Query attacks often require a large number of queries for success. To achieve the best of both approaches, recent efforts have tried to combine them, but still require hundreds of queries to achieve high success rates (especially for targeted attacks). In this paper, we propose a novel method for Blackbox Attacks via Surrogate Ensemble Search (BASES) that can generate highly s…
Tsinghua University（清华大学）；Mila（米拉研究所）；HEC Montreal（蒙特利尔高等商学院）；UIUC（伊利诺伊大学厄巴纳-香槟分校）；University of Michigan（密歇根大学）；University of California, Berkeley（加州大学伯克利分校）
Unsupervised node embedding methods (e.g., DeepWalk, LINE, and node2vec) have attracted growing interests given their simplicity and effectiveness. However, although these methods have been proved effective in a variety of applications, none of the existing work has analyzed the robustness of them. This could be very risky if these methods are attacked by an adversarial party. In this paper, we take the task of link prediction as an example, which is one of the most fundamental problems for graph analysis, and introduce a data positioning attack to node embedding methods. We give a complete ch…
Gradient-based learning algorithms have an implicit simplicity bias which in effect can limit the diversity of predictors being sampled by the learning procedure. This behavior can hinder the transferability of trained models by (i) favoring the learning of simpler but spurious features -- present in the training data but absent from the test data -- and (ii) by only leveraging a small subset of predictive features. Such an effect is especially magnified when the test distribution does not exactly match the train distribution -- referred to as the Out of Distribution (OOD) generalization probl…
We propose an intriguingly simple method for the construction of adversarial images in the black-box setting. In constrast to the white-box scenario, constructing black-box adversarial images has the additional constraint on query budget, and efficient attacks remain an open problem to date. With only the mild assumption of continuous-valued confidence scores, our highly query-efficient algorithm utilizes the following simple iterative principle: we randomly sample a vector from a predefined orthonormal basis and either add or subtract it to the target image. Despite its simplicity, the propos…
Deep learning approaches show promise for predicting childhood malnutrition: A comparative study with traditional machine learning methods using survey data
Department of Mathematics and Statistics, Florida Atlantic University（数学与统计学系，佛罗里达 Atlantic 大学）
