Note on Attacking Object Detectors with Adversarial Stickers
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）
Kevin Eykholt, Ivan Evtimov, Earlence Fernandes, Bo Li, Dawn Song, Tadayoshi Kohno, Amir Rahmati, Atul Prakash, Florian Tramer
备注：
Short Note: The full version of this paper was accepted to USENIX WOOT 2018, and is available at arXiv:1807.07769
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 objection detection algorithms are harder to be fooled by the same set of adversarial examples, here we show that these detectors can also be attacked by physical adversarial examples. In this note, we briefly show both static and dynamic test results. We design an algorithm that produces physical adversarial inputs, which can fool the YOLO object detector and can also attack Faster-RCNN with relatively high success rate based on transferability. Furthermore, our algorithm can compress the size of the adversarial inputs to stickers that, when attached to the targeted object, result in the detector either mislabeling or not detecting the object a high percentage of the time. This note provides a small set of results. Our upcoming paper will contain a thorough evaluation on other object detectors, and will present the algorithm.
University of Michigan（密歇根大学）；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）；Samsung Research America（三星美国研究院）
Deep neural networks (DNNs) are vulnerable to adversarial examples-maliciously crafted inputs that cause DNNs to make incorrect predictions. Recent work has shown that these attacks generalize to the physical domain, to create perturbations on physical objects that fool image classifiers under a variety of real-world conditions. Such attacks pose a risk to deep learning models used in safety-critical cyber-physical systems. In this work, we extend physical attacks to more challenging object detection models, a broader class of deep learning algorithms widely used to detect and label multiple o…
Universal Multi-view Black-box Attack against Object Detectors via Layout Optimization
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Defense Innovation Institute, Chinese Academy of Military Science（中国人民解放军军事科学院国防创新研究院）；School of Automation and Electrical Engineering, Zhongyuan University of Technology（中原工学院自动化与电气工程学院）
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…
Adversarial patch attacks mislead neural networks by injecting adversarial pixels within a local region. Patch attacks can be highly effective in a variety of tasks and physically realizable via attachment (e.g. a sticker) to the real-world objects. Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images. We exploit this property and present PatchZero, a general defense pipeline against white-box adversarial patches without retraining the downstream classifier or detector. Specifically, our defense detects adversa…
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…
Georgia Institute of Technology（佐治亚理工学院）；Intel Corporation（英特尔公司）
Given the ability to directly manipulate image pixels in the digital input space, an adversary can easily generate imperceptible perturbations to fool a Deep Neural Network (DNN) image classifier, as demonstrated in prior work. In this work, we propose ShapeShifter, an attack that tackles the more challenging problem of crafting physical adversarial perturbations to fool image-based object detectors like Faster R-CNN. Attacking an object detector is more difficult than attacking an image classifier, as it needs to mislead the classification results in multiple bounding boxes with different sca…
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…
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.…
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…
Bosch Center for Artificial Intelligence（博世人工智能中心）；Carnegie Mellon University（卡内基梅隆大学）
Recent work has documented the susceptibility of deep learning systems to adversarial examples, but most such attacks directly manipulate the digital input to a classifier. Although a smaller line of work considers physical adversarial attacks, in all cases these involve manipulating the object of interest, e.g., putting a physical sticker on an object to misclassify it, or manufacturing an object specifically intended to be misclassified. In this work, we consider an alternative question: is it possible to fool deep classifiers, over all perceived objects of a certain type, by physically mani…
Unleashing the Representational Power of Fourier Shapes for Attacking Infrared Object Detection
School of Information and Communications Engineering, Faculty of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an, China（信息与通信工程学院，电子与信息工程学院，西安交通大学，西安，中国）；School of Physics, Xi'an Jiaotong University, Xi'an, China（物理学院，西安交通大学，西安，中国）
Recently, physical domain adversarial attacks have drawn significant attention from the machine learning community. One important attack proposed by Eykholt et al. can fool a classifier by placing black and white stickers on an object such as a road sign. While this attack may pose a significant threat to visual classifiers, there are currently no defenses designed to protect against this attack. In this paper, we propose new defenses that can protect against multi-sticker attacks. We present defensive strategies capable of operating when the defender has full, partial, and no prior informatio…
Blind spots or outright deceit can bedevil and deceive machine learning models. Unidentified objects such as digital "stickers," also known as adversarial patches, can fool facial recognition systems, surveillance systems and self-driving cars. Fortunately, most existing adversarial patches can be outwitted, disabled and rejected by a simple classification network called an adversarial patch detector, which distinguishes adversarial patches from original images. An object detector classifies and predicts the types of objects within an image, such as by distinguishing a motorcyclist from the mo…
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 …
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…
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…
Auburn University（奥本大学）；Florida International University（佛罗里达国际大学）
Universal Adversarial Perturbations are image-agnostic and model-independent noise that when added with any image can mislead the trained Deep Convolutional Neural Networks into the wrong prediction. Since these Universal Adversarial Perturbations can seriously jeopardize the security and integrity of practical Deep Learning applications, existing techniques use additional neural networks to detect the existence of these noises at the input image source. In this paper, we demonstrate an attack strategy that when activated by rogue means (e.g., malware, trojan) can bypass these existing counter…
Tencent（腾讯）；Zhejiang University（浙江大学）；JD Explore Academy（京东探索研究院）；University of Munich（慕尼黑大学）
It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we find that the adversarial attacks can also be vulnerable to small perturbations. Namely, on adversarially-trained models, perturbing adversarial examples with a small random noise may invalidate their misled predictions. After carefully examining state-of-the-art attacks of various kinds, we find that all these attacks have this deficiency to different exten…
Adversarial attack breaks the boundaries of traditional security defense. For adversarial attack and the characteristics of cloud services, we propose Security Development Lifecycle for Machine Learning applications, e.g., SDL for ML. The SDL for ML helps developers build more secure software by reducing the number and severity of vulnerabilities in ML-as-a-service, while reducing development cost.
Machine learning models are known to be vulnerable to adversarial perturbations in the input domain, causing incorrect predictions. Inspired by this phenomenon, we explore the feasibility of manipulating EEG-based Motor Imagery (MI) Brain Computer Interfaces (BCIs) via perturbations in sensory stimuli. Similar to adversarial examples, these \emph{adversarial stimuli} aim to exploit the limitations of the integrated brain-sensor-processing components of the BCI system in handling shifts in participants' response to changes in sensory stimuli. This paper proposes adversarial stimuli as an attack…
The Madry Lab recently hosted a competition designed to test the robustness of their adversarially trained MNIST model. Attacks were constrained to perturb each pixel of the input image by a scaled maximal $L_\infty$ distortion $ε$ = 0.3. This discourages the use of attacks which are not optimized on the $L_\infty$ distortion metric. Our experimental results demonstrate that by relaxing the $L_\infty$ constraint of the competition, the elastic-net attack to deep neural networks (EAD) can generate transferable adversarial examples which, despite their high average $L_\infty$ distortion, have mi…
Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a principled way and study the robustness of DRL policies to adversarial attacks from the perspective of robust optimization. Within the framework of robust optimization, optimal adversarial attacks are given by minimizing the expected return of the policy, and correspondingly a good defense mechanism should be realized by improving the worst-case performance of the policy. Considering …
Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another agent's observations. This might lead one to wonder: is it possible to attack an RL agent simply by choosing an adversarial policy acting in a multi-agent environment so as to create natural observations that are adversarial? We demonstrate the existence of adversarial policies in zero-sum games between simulated humanoid robots with proprioceptive observation…
University of Science and Technology of China（中国科学技术大学）；The Chinese University of Hong Kong（香港中文大学）；The Chinese Academy of Sciences（中国科学院）；The University of Hong Kong（香港大学）
Modern deep neural networks are often vulnerable to adversarial samples. Based on the first optimization-based attacking method, many following methods are proposed to improve the attacking performance and speed. Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods. However, current generation-based methods are only able to attack one specific target (category) within one model, thus making th…
Adversarial attacking aims to fool deep neural networks with adversarial examples. In the field of natural language processing, various textual adversarial attack models have been proposed, varying in the accessibility to the victim model. Among them, the attack models that only require the output of the victim model are more fit for real-world situations of adversarial attacking. However, to achieve high attack performance, these models usually need to query the victim model too many times, which is neither efficient nor viable in practice. To tackle this problem, we propose a reinforcement l…
Since the threat of malicious software (malware) has become increasingly serious, automatic malware detection techniques have received increasing attention, where machine learning (ML)-based visualization detection methods become more and more popular. In this paper, we demonstrate that the state-of-the-art ML-based visualization detection methods are vulnerable to Adversarial Example (AE) attacks. We develop a novel Adversarial Texture Malware Perturbation Attack (ATMPA) method based on the gradient descent and L-norm optimization method, where attackers can introduce some tiny perturbations …
Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. We consider this as a new type of adversarial attack in NLP, a setting to which humans are very robust, as our experiments with both simple and more difficult visual input perturbations demonstrate. We then investigate the impact of visual adversarial attacks on current NLP systems on character-, word-, and sentence-level tasks, showing that both neural and non-neural models are, in contrast to humans, extremely sensi…
Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
Lehigh University（莱文大学）；University of Minnesota Twin Cities（明尼苏达大学双城分校）；North Carolina State University（北卡罗来纳州立大学）；University of Rhode Island（罗德岛大学）；Northeastern University（东北大学）
University of Shanghai for Science and Technology（上海理工大学）；State Street Corporation（道富公司）；Guangzhou University（广州大学）；Fudan University（复旦大学）；Qingdao Binhai University（青岛滨海学院）
Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make mistake. It always involves a defending side, usually a classifier, and an attacking side that aims to cause incorrect output. The earliest studies on the adversarial examples for machine learning algorithms start from the information security area, which considers a much wider varieties of attacking methods. But recent research focus that popularized by th…
Shanghai AI Lab（上海人工智能实验室）；University of Maryland, College Park（马里兰大学帕克分校）
Recent studies reveal that a well-trained deep reinforcement learning (RL) policy can be particularly vulnerable to adversarial perturbations on input observations. Therefore, it is crucial to train RL agents that are robust against any attacks with a bounded budget. Existing robust training methods in deep RL either treat correlated steps separately, ignoring the robustness of long-term rewards, or train the agents and RL-based attacker together, doubling the computational burden and sample complexity of the training process. In this work, we propose a strong and efficient robust training fra…
Adversarial samples for images have been extensively studied in the literature. Among many of the attacking methods, gradient-based methods are both effective and easy to compute. In this work, we propose a framework to adapt the gradient attacking methods on images to text domain. The main difficulties for generating adversarial texts with gradient methods are i) the input space is discrete, which makes it difficult to accumulate small noise directly in the inputs, and ii) the measurement of the quality of the adversarial texts is difficult. We tackle the first problem by searching for advers…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Google（谷歌）；Mila - Quebec Artificial Intelligence Institute（米拉-魁北克人工智能研究所）
There has been emerging interest to use transductive learning for adversarial robustness (Goldwasser et al., NeurIPS 2020; Wu et al., ICML 2020). Compared to traditional "test-time" defenses, these defense mechanisms "dynamically retrain" the model based on test time input via transductive learning; and theoretically, attacking these defenses boils down to bilevel optimization, which seems to raise the difficulty for adaptive attacks. In this paper, we first formalize and analyze modeling aspects of transductive robustness. Then, we propose the principle of attacking model space for solving bi…
Tsinghua University（清华大学）；Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Tencent AI Lab（腾讯人工智能实验室）；University of Electronic Science and Technology of China（电子科技大学）
In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget. Due to the limited feedback information, existing query-based black-box attack methods often require many queries for attacking each benign example. To reduce query cost, we propose to utilize the feedback information across historical attacks, dubbed example-level adversarial transferability. Specifically, by treating the attack on each benign example as one task, we develop a meta-learning…
Physical adversarial examples for camera-based computer vision have so far been achieved through visible artifacts -- a sticker on a Stop sign, colorful borders around eyeglasses or a 3D printed object with a colorful texture. An implicit assumption here is that the perturbations must be visible so that a camera can sense them. By contrast, we contribute a procedure to generate, for the first time, physical adversarial examples that are invisible to human eyes. Rather than modifying the victim object with visible artifacts, we modify light that illuminates the object. We demonstrate how an att…
Recently, adversarial attacks for audio recognition have attracted much attention. However, most of the existing studies mainly rely on the coarse-grain audio features at the instance level to generate adversarial noises, which leads to expensive generation time costs and weak universal attacking ability. Motivated by the observations that all audio speech consists of fundamental phonemes, this paper proposes a phonemic adversarial tack (PAT) paradigm, which attacks the fine-grain audio features at the phoneme level commonly shared across audio instances, to generate phonemic adversarial noise…
Recommendation Systems (RS) have become an essential part of many online services. Due to its pivotal role in guiding customers towards purchasing, there is a natural motivation for unscrupulous parties to spoof RS for profits. In this paper, we study the shilling attack: a subsistent and profitable attack where an adversarial party injects a number of user profiles to promote or demote a target item. Conventional shilling attack models are based on simple heuristics that can be easily detected, or directly adopt adversarial attack methods without a special design for RS. Moreover, the study o…
Tsinghua-Berkeley Shenzhen Institute, Tsinghua University（清华大学清华-伯克利深圳学院）；Tencent AI Lab（腾讯人工智能实验室）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
With the great success of graph embedding model on both academic and industry area, the robustness of graph embedding against adversarial attack inevitably becomes a central problem in graph learning domain. Regardless of the fruitful progress, most of the current works perform the attack in a white-box fashion: they need to access the model predictions and labels to construct their adversarial loss. However, the inaccessibility of model predictions in real systems makes the white-box attack impractical to real graph learning system. This paper promotes current frameworks in a more general and…
We introduce two tactics to attack agents trained by deep reinforcement learning algorithms using adversarial examples, namely the strategically-timed attack and the enchanting attack. In the strategically-timed attack, the adversary aims at minimizing the agent's reward by only attacking the agent at a small subset of time steps in an episode. Limiting the attack activity to this subset helps prevent detection of the attack by the agent. We propose a novel method to determine when an adversarial example should be crafted and applied. In the enchanting attack, the adversary aims at luring the …
In this paper, we study the vulnerability of anti-spoofing methods based on deep learning against adversarial perturbations. We first show that attacking a CNN-based anti-spoofing face authentication system turns out to be a difficult task. When a spoofed face image is attacked in the physical world, in fact, the attack has not only to remove the rebroadcast artefacts present in the image, but it has also to take into account that the attacked image will be recaptured again and then compensate for the distortions that will be re-introduced after the attack by the subsequent rebroadcast process…
Virginia Tech（弗吉尼亚理工大学）；University of Virginia（弗吉尼亚大学）
Advances in deep neural networks (DNNs) have shown tremendous promise in the medical domain. However, the deep learning tools that are helping the domain, can also be used against it. Given the prevalence of fraud in the healthcare domain, it is important to consider the adversarial use of DNNs in manipulating sensitive data that is crucial to patient healthcare. In this work, we present the design and implementation of a DNN-based image translation attack on biomedical imagery. More specifically, we propose Jekyll, a neural style transfer framework that takes as input a biomedical image of a …
University of Michigan（密歇根大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；IBM Research（IBM研究院）；University of California, Los Angeles（加州大学洛杉矶分校）；JD AI Research（京东人工智能研究院）；National Taiwan University of Science and Technology（台湾科技大学）
Recent studies have shown that adversarial examples in state-of-the-art image classifiers trained by deep neural networks (DNN) can be easily generated when the target model is transparent to an attacker, known as the white-box setting. However, when attacking a deployed machine learning service, one can only acquire the input-output correspondences of the target model; this is the so-called black-box attack setting. The major drawback of existing black-box attacks is the need for excessive model queries, which may give a false sense of model robustness due to inefficient query designs. To bri…
The Hong Kong Polytechnic University（香港理工大学）；Michigan State University（密歇根州立大学）；The Pennsylvania State University（宾夕法尼亚州立大学）；City University of Hong Kong（香港城市大学）；IBM T.J. Watson（IBM托马斯·J·沃森研究中心）
Graph Neural Networks (GNNs) have boosted the performance for many graph-related tasks. Despite the great success, recent studies have shown that GNNs are highly vulnerable to adversarial attacks, where adversaries can mislead the GNNs' prediction by modifying graphs. On the other hand, the explanation of GNNs (GNNExplainer) provides a better understanding of a trained GNN model by generating a small subgraph and features that are most influential for its prediction. In this paper, we first perform empirical studies to validate that GNNExplainer can act as an inspection tool and have the poten…
Modern commercial antivirus systems increasingly rely on machine learning to keep up with the rampant inflation of new malware. However, it is well-known that machine learning models are vulnerable to adversarial examples (AEs). Previous works have shown that ML malware classifiers are fragile to the white-box adversarial attacks. However, ML models used in commercial antivirus products are usually not available to attackers and only return hard classification labels. Therefore, it is more practical to evaluate the robustness of ML models and real-world AVs in a pure black-box manner. We propo…
Huazhong University of Science and Technology（华中科技大学）
Most current methods generate adversarial examples with the $L_p$ norm specification. As a result, many defense methods utilize this property to eliminate the impact of such attacking algorithms. In this paper,we instead introduce "unrestricted" perturbations that create adversarial samples by using spurious relations which were learned by model training. Specifically, we find feature clusters in non-semantic features that are strongly correlated with model judgment results, and treat them as spurious relations learned by the model. Then we create adversarial samples by using them to replace t…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Peking University（北京大学）；University of Texas at Dallas（德克萨斯大学达拉斯分校）
Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose potential risks on safety and security critical applications. However, existing defense approaches are still vulnerable to attacks, especially in a white-box attack scenario. To address this issue, we propose a new defense approach, named MulDef, based on robustness diversity. Our approach consists of (1) a general defense framework based on multiple models and…
