Ongoing research has proposed several methods to defend neural networks against adversarial examples, many of which researchers have shown to be ineffective. We ask whether a strong defense can be created by combining multiple (possibly weak) defenses. To answer this question, we study three defenses that follow this approach. Two of these are recently proposed defenses that intentionally combine components designed to work well together. A third defense combines three independent defenses. For all the components of these defenses and the combined defenses themselves, we show that an adaptive adversary can create adversarial examples successfully with low distortion. Thus, our work implies that ensemble of weak defenses is not sufficient to provide strong defense against adversarial examples.
Wavestone；Facebook AI Research（Facebook人工智能研究院）；CEA, Université Paris-Saclay（法国原子能和替代能源委员会，巴黎-萨克雷大学）；PSL, Université Paris-Dauphine（巴黎文理研究大学，巴黎多芬纳大学）
It has been empirically observed that defense mechanisms designed to protect neural networks against $\ell_\infty$ adversarial examples offer poor performance against $\ell_2$ adversarial examples and vice versa. In this paper we conduct a geometrical analysis that validates this observation. Then, we provide a number of empirical insights to illustrate the effect of this phenomenon in practice. Then, we review some of the existing defense mechanism that attempts to defend against multiple attacks by mixing defense strategies. Thanks to our numerical experiments, we discuss the relevance of th…
Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of undermining a system. In the case of DNNs, the lack of better understanding of their working has prevented the development of efficient defenses. In this paper, we propose a new defense method based on practical observations which is easy to integrate into models and performs better than state-of-the-art defenses. Our proposed solution is meant to reinfo…
Previous studies demonstrate DNNs' vulnerability to adversarial examples and adversarial training can establish a defense to adversarial examples. In addition, recent studies show that deep neural networks also exhibit vulnerability to parameter corruptions. The vulnerability of model parameters is of crucial value to the study of model robustness and generalization. In this work, we introduce the concept of parameter corruption and propose to leverage the loss change indicators for measuring the flatness of the loss basin and the parameter robustness of neural network parameters. On such basi…
MagNet and "Efficient Defenses..." were recently proposed as a defense to adversarial examples. We find that we can construct adversarial examples that defeat these defenses with only a slight increase in distortion.
South China University of Technology（华南理工大学）；ETH Zürich（苏黎世联邦理工学院）；National University of Singapore（新加坡国立大学）
Deep neural networks (DNNs) are vulnerable to adversarial examples with small perturbations. Adversarial defense thus has been an important means which improves the robustness of DNNs by defending against adversarial examples. Existing defense methods focus on some specific types of adversarial examples and may fail to defend well in real-world applications. In practice, we may face many types of attacks where the exact type of adversarial examples in real-world applications can be even unknown. In this paper, motivated by that adversarial examples are more likely to appear near the classifica…
Advances in the development of adversarial attacks have been fundamental to the progress of adversarial defense research. Efficient and effective attacks are crucial for reliable evaluation of defenses, and also for developing robust models. Adversarial attacks are often generated by maximizing standard losses such as the cross-entropy loss or maximum-margin loss within a constraint set using Projected Gradient Descent (PGD). In this work, we introduce a relaxation term to the standard loss, that finds more suitable gradient-directions, increases attack efficacy and leads to more efficient adv…
Peking University（北京大学）；National Tsinghua University（国立清华大学）；UC San Diego（加州大学圣地亚哥分校）
We propose an adversarial defense method that achieves state-of-the-art performance among attack-agnostic adversarial defense methods while also maintaining robustness to input resolution, scale of adversarial perturbation, and scale of dataset size. Based on convolutional sparse coding, we construct a stratified low-dimensional quasi-natural image space that faithfully approximates the natural image space while also removing adversarial perturbations. We introduce a novel Sparse Transformation Layer (STL) in between the input image and the first layer of the neural network to efficiently proj…
Stony Brook University（石溪大学）；IBM Research（IBM研究院）；University of Michingan（密歇根大学）
Adversarial machine learning is a well-studied field of research where an adversary causes predictable errors in a machine learning algorithm through precise manipulation of the input. Numerous techniques have been proposed to harden machine learning algorithms and mitigate the effect of adversarial attacks. Of these techniques, adversarial training, which augments the training data with adversarial samples, has proven to be an effective defense with respect to a certain class of attacks. However, adversarial training is computationally expensive and its improvements are limited to a single mo…
Graph neural networks (GNNs) achieve remarkable performance for tasks on graph data. However, recent works show they are extremely vulnerable to adversarial structural perturbations, making their outcomes unreliable. In this paper, we propose DefenseVGAE, a novel framework leveraging variational graph autoencoders(VGAEs) to defend GNNs against such attacks. DefenseVGAE is trained to reconstruct graph structure. The reconstructed adjacency matrix can reduce the effects of adversarial perturbations and boost the performance of GCNs when facing adversarial attacks. Our experiments on a number of …
Several recent papers have discussed utilizing Lipschitz constants to limit the susceptibility of neural networks to adversarial examples. We analyze recently proposed methods for computing the Lipschitz constant. We show that the Lipschitz constant may indeed enable adversarially robust neural networks. However, the methods currently employed for computing it suffer from theoretical and practical limitations. We argue that addressing this shortcoming is a promising direction for future research into certified adversarial defenses.
Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy multiple simultaneous constraints often over-optimize against one constraint at the cost of satisfying another. We introduce Orthogonal Projected Gradient Descent, an improved attack technique to generate adversarial examples that avoids this problem by orthogonalizing the gradients when running standard gradient-based attacks. We use our technique to evade fo…
A recent defense proposes to inject "honeypots" into neural networks in order to detect adversarial attacks. We break the baseline version of this defense by reducing the detection true positive rate to 0\% and the detection AUC to 0.02, maintaining the original distortion bounds. The authors of the original paper have amended the defense in their CCS'20 paper to mitigate this attacks. To aid further research, we release the complete 2.5 hour keystroke-by-keystroke screen recording of our attack process at https://nicholas.carlini.com/code/ccs_honeypot_break.
I introduce a very simple method to defend against adversarial examples. The basic idea is to raise the slope of the ReLU function at the test time. Experiments over MNIST and CIFAR-10 datasets demonstrate the effectiveness of the proposed defense against a number of strong attacks in both untargeted and targeted settings. While perhaps not as effective as the state of the art adversarial defenses, this approach can provide insights to understand and mitigate adversarial attacks. It can also be used in conjunction with other defenses.
Georg-August University of Göttingen（哥廷根乔治-奥古斯特大学）；University of Tübingen（图宾根大学）
A recent paper by Liu et al. combines the topics of adversarial training and Bayesian Neural Networks (BNN) and suggests that adversarially trained BNNs are more robust against adversarial attacks than their non-Bayesian counterparts. Here, I analyze the proposed defense and suggest that one needs to adjust the adversarial attack to incorporate the stochastic nature of a Bayesian network to perform an accurate evaluation of its robustness. Using this new type of attack I show that there appears to be no strong evidence for higher robustness of the adversarially trained BNNs.
USC Ming Hsieh Department of Electrical and Computer Engineering（南加州大学明谢电子与计算机工程系）
A variety of recent works have looked into defenses for deep neural networks against adversarial attacks particularly within the image processing domain. Speech processing applications such as automatic speech recognition (ASR) are increasingly relying on deep learning models, and so are also prone to adversarial attacks. However, many of the defenses explored for ASR simply adapt the image-domain defenses, which may not provide optimal robustness. This paper explores speech specific defenses using the mel spectral domain, and introduces a novel defense method called 'mel domain noise flooding…
In recent years, deep neural networks have demonstrated outstanding performance in many machine learning tasks. However, researchers have discovered that these state-of-the-art models are vulnerable to adversarial examples: legitimate examples added by small perturbations which are unnoticeable to human eyes. Adversarial training, which augments the training data with adversarial examples during the training process, is a well known defense to improve the robustness of the model against adversarial attacks. However, this robustness is only effective to the same attack method used for adversari…
Conventional adversarial defenses reduce classification accuracy whether or not a model is under attacks. Moreover, most of image processing based defenses are defeated due to the problem of obfuscated gradients. In this paper, we propose a new adversarial defense which is a defensive transform for both training and test images inspired by perceptual image encryption methods. The proposed method utilizes a block-wise pixel shuffling method with a secret key. The experiments are carried out on both adaptive and non-adaptive maximum-norm bounded white-box attacks while considering obfuscated gra…
Dataset bias is a problem in adversarial machine learning, especially in the evaluation of defenses. An adversarial attack or defense algorithm may show better results on the reported dataset than can be replicated on other datasets. Even when two algorithms are compared, their relative performance can vary depending on the dataset. Deep learning offers state-of-the-art solutions for image recognition, but deep models are vulnerable even to small perturbations. Research in this area focuses primarily on adversarial attacks and defense algorithms. In this paper, we report for the first time, a …
In the literature on adversarial examples, white box and black box attacks have received the most attention. The adversary is assumed to have either full (white) or no (black) access to the defender's model. In this work, we focus on the equally practical gray box setting, assuming an attacker has partial information. We propose a novel defense that assumes everything but a private key will be made available to the attacker. Our framework uses an image denoising procedure coupled with encryption via a discretized Baker map. Extensive testing against adversarial images (e.g. FGSM, PGD) crafted …
There has been extensive research on developing defense techniques against adversarial attacks; however, they have been mainly designed for specific model families or application domains, therefore, they cannot be easily extended. Based on the design philosophy of ensemble of diverse weak defenses, we propose ATHENA---a flexible and extensible framework for building generic yet effective defenses against adversarial attacks. We have conducted a comprehensive empirical study to evaluate several realizations of ATHENA with four threat models including zero-knowledge, black-box, gray-box, and whi…
Spiking neural networks (SNNs) attract great attention due to their low power consumption, low latency, and biological plausibility. As they are widely deployed in neuromorphic devices for low-power brain-inspired computing, security issues become increasingly important. However, compared to deep neural networks (DNNs), SNNs currently lack specifically designed defense methods against adversarial attacks. Inspired by neural membrane potential oscillation, we propose a novel neural model that incorporates the bio-inspired oscillation mechanism to enhance the security of SNNs. Our experiments sh…
Recently, researchers have discovered that the state-of-the-art object classifiers can be fooled easily by small perturbations in the input unnoticeable to human eyes. It is also known that an attacker can generate strong adversarial examples if she knows the classifier parameters. Conversely, a defender can robustify the classifier by retraining if she has access to the adversarial examples. We explain and formulate this adversarial example problem as a two-player continuous zero-sum game, and demonstrate the fallacy of evaluating a defense or an attack as a static problem. To find the best w…
DCI-Solutions；U.S. Army Combat Capabilities Development Command (CCDC), C5ISR Center（美国陆军作战能力发展司令部（CCDC）C5ISR中心）
There has been considerable and growing interest in applying machine learning for cyber defenses. One promising approach has been to apply natural language processing techniques to analyze logs data for suspicious behavior. A natural question arises to how robust these systems are to adversarial attacks. Defense against sophisticated attack is of particular concern for cyber defenses. In this paper, we develop a testing framework to evaluate adversarial robustness of machine learning cyber defenses, particularly those focused on log data. Our framework uses techniques from deep reinforcement l…
Several moving target defenses (MTDs) to counter adversarial ML attacks have been proposed in recent years. MTDs claim to increase the difficulty for the attacker in conducting attacks by regularly changing certain elements of the defense, such as cycling through configurations. To examine these claims, we study for the first time the effectiveness of several recent MTDs for adversarial ML attacks applied to the malware detection domain. Under different threat models, we show that transferability and query attack strategies can achieve high levels of evasion against these defenses through exis…
Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense's inner workings or approaches based on an ensemble of fixed attacks, none of which may be effective for the specific defense at hand. Our key observation is that adaptive attacks are composed of reusable building blocks that can be formalized in a search space and used to automatically discover attacks for unknown defenses. We evaluated our approach on 24 adversarial defenses and show that it outperforms AutoAttack, the current state-of-the-art…
Under adversarial attacks, time series regression and classification are vulnerable. Adversarial defense, on the other hand, can make the models more resilient. It is important to evaluate how vulnerable different time series models are to attacks and how well they recover using defense. The sensitivity to various attacks and the robustness using the defense of several time series models are investigated in this study. Experiments are run on seven-time series models with three adversarial attacks and one adversarial defense. According to the findings, all models, particularly GRU and RNN, appe…
In recent years, Deep Neural Networks (DNNs) have had a dramatic impact on a variety of problems that were long considered very difficult, e. g., image classification and automatic language translation to name just a few. The accuracy of modern DNNs in classification tasks is remarkable indeed. At the same time, attackers have devised powerful methods to construct specially-crafted malicious inputs (often referred to as adversarial examples) that can trick DNNs into mis-classifying them. What is worse is that despite the many defense mechanisms proposed to protect DNNs against adversarial atta…
Shenzhen Youjia Innov Tech Co., Ltd（深圳佑驾创新科技有限公司）；South China University of Technology（华南理工大学）；Hong Kong University of Science and Technology（香港科技大学）
Deep neural networks (DNNs) are known to be vulnerable to adversarial attacks that would trigger misclassification of DNNs but may be imperceptible to human perception. Adversarial defense has been an important way to improve the robustness of DNNs. Existing attack methods often construct adversarial examples relying on some metrics like the $\ell_p$ distance to perturb samples. However, these metrics can be insufficient to conduct adversarial attacks due to their limited perturbations. In this paper, we propose a new internal Wasserstein distance (IWD) to capture the semantic similarity of tw…
Adversarial attacks optimize against models to defeat defenses. Existing defenses are static, and stay the same once trained, even while attacks change. We argue that models should fight back, and optimize their defenses against attacks at test time. We propose dynamic defenses, to adapt the model and input during testing, by defensive entropy minimization (dent). Dent alters testing, but not training, for compatibility with existing models and train-time defenses. Dent improves the robustness of adversarially-trained defenses and nominally-trained models against white-box, black-box, and adap…
Research in adversarial learning follows a cat and mouse game between attackers and defenders where attacks are proposed, they are mitigated by new defenses, and subsequently new attacks are proposed that break earlier defenses, and so on. However, it has remained unclear as to whether there are conditions under which no better attacks or defenses can be proposed. In this paper, we propose a game-theoretic framework for studying attacks and defenses which exist in equilibrium. Under a locally linear decision boundary model for the underlying binary classifier, we prove that the Fast Gradient M…
Adversarial examples reveal the vulnerability and unexplained nature of neural networks. Studying the defense of adversarial examples is of considerable practical importance. Most adversarial examples that misclassify networks are often undetectable by humans. In this paper, we propose a defense model to train the classifier into a human-perception classification model with shape preference. The proposed model comprising a texture transfer network (TTN) and an auxiliary defense generative adversarial networks (GAN) is called Human-perception Auxiliary Defense GAN (HAD-GAN). The TTN is used to …
A No-Defense Defense Against Gradient-Based Adversarial Attacks on ML-NIDS: Is Less More?
Carleton University（卡尔顿大学）；Computer Engineering Carleton University Ottawa, Canada（计算机工程系卡尔顿大学渥太华加拿大）；School of Information Technology Carleton University Ottawa, Canada（信息科技学院卡尔顿大学渥太华加拿大）
Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble framework and a suite of robust defense algorithms, which are attack-independent, and capable of auto-repairing and auto-verifying the target model being attacked. Our strategic ensemble approach makes three original contributions. First, we employ input-transformation diversity to …
Deep learning has become the state of the art approach in many machine learning problems such as classification. It has recently been shown that deep learning is highly vulnerable to adversarial perturbations. Taking the camera systems of self-driving cars as an example, small adversarial perturbations can cause the system to make errors in important tasks, such as classifying traffic signs or detecting pedestrians. Hence, in order to use deep learning without safety concerns a proper defense strategy is required. We propose to use ensemble methods as a defense strategy against adversarial per…
Guangzhou University（广州大学）；Cyberspace Institute of Advanced Technology（网络空间先进技术研究院）
Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection methods usually make assumptions about the adversarial example and attack method (e.g., the word frequency of the adversarial example, the perturbation level of the attack method). However, this limits the applicability of the detection method. To this end, we propose TREATED, a universal adversarial detection method that can defend against attacks of various pert…
University of Central Florida（中佛罗里达大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
The vulnerability of deep networks to adversarial attacks is a central problem for deep learning from the perspective of both cognition and security. The current most successful defense method is to train a classifier using adversarial images created during learning. Another defense approach involves transformation or purification of the original input to remove adversarial signals before the image is classified. We focus on defending naturally-trained classifiers using Markov Chain Monte Carlo (MCMC) sampling with an Energy-Based Model (EBM) for adversarial purification. In contrast to advers…
Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks. This increases the importance of robust training of 3D models in the face of adversarial attacks. Based on our analysis on the performance of existing adversarial attacks, more adversarial perturbations are found in the mid and high-frequency components of input data. Therefore, by suppressing the high-frequency content in the training phase, the models robustness against adversarial examples is improved. Experiments showed that the pr…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；TU Kaiserslautern（凯撒斯劳滕工业大学）
The adversarial vulnerability of deep networks has spurred the interest of researchers worldwide. Unsurprisingly, like images, adversarial examples also translate to time-series data as they are an inherent weakness of the model itself rather than the modality. Several attempts have been made to defend against these adversarial attacks, particularly for the visual modality. In this paper, we perform detailed benchmarking of well-proven adversarial defense methodologies on time-series data. We restrict ourselves to the $L_{\infty}$ threat model. We also explore the trade-off between smoothness …
University of Connecticut（康涅狄格大学）；CWI（荷兰国家数学与计算机科学研究所）；eBay
Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine black-box attacks. In this paper, we expand upon the analysis of these defenses to include adaptive black-box adversaries. Our evaluation is done on nine defenses including Barrage of Random Transforms, ComDefend, Ensemble Diversity, Feature Distillation, The Odds are Odd, Error Correcting Codes, Distribution Classifier Defense, K-Winner Take All and Buffer Zones. Our investigation is done using two black-box adversa…
The adversarial attacks against deep neural networks on computer vision tasks have spawned many new technologies that help protect models from avoiding false predictions. Recently, word-level adversarial attacks on deep models of Natural Language Processing (NLP) tasks have also demonstrated strong power, e.g., fooling a sentiment classification neural network to make wrong decisions. Unfortunately, few previous literatures have discussed the defense of such word-level synonym substitution based attacks since they are hard to be perceived and detected. In this paper, we shed light on this prob…
National Taiwan University（台湾大学）；The Chinese University of Hong Kong（香港中文大学）
Various forefront countermeasure methods for automatic speaker verification (ASV) with considerable performance in anti-spoofing are proposed in the ASVspoof 2019 challenge. However, previous work has shown that countermeasure models are vulnerable to adversarial examples indistinguishable from natural data. A good countermeasure model should not only be robust against spoofing audio, including synthetic, converted, and replayed audios; but counteract deliberately generated examples by malicious adversaries. In this work, we introduce a passive defense method, spatial smoothing, and a proactiv…
In spite of the enormous success of neural networks, adversarial examples remain a relatively weakly understood feature of deep learning systems. There is a considerable effort in both building more powerful adversarial attacks and designing methods to counter the effects of adversarial examples. We propose a method to transform the adversarial input data through a mixture of generators in order to recover the correct class obfuscated by the adversarial attack. A canonical set of images is used to generate adversarial examples through potentially multiple attacks. Such transformed images are p…
As the applications of deep reinforcement learning (DRL) in wireless communications grow, sensitivity of DRL based wireless communication strategies against adversarial attacks has started to draw increasing attention. In order to address such sensitivity and alleviate the resulting security concerns, we in this paper consider a victim user that performs DRL-based dynamic channel access, and an attacker that executes DRLbased jamming attacks to disrupt the victim. Hence, both the victim and attacker are DRL agents and can interact with each other, retrain their models, and adapt to opponents' …
Huazhong University of Science and Technology（华中科技大学）
In the area of natural language processing, deep learning models are recently known to be vulnerable to various types of adversarial perturbations, but relatively few works are done on the defense side. Especially, there exists few effective defense method against the successful synonym substitution based attacks that preserve the syntactic structure and semantic information of the original text while fooling the deep learning models. We contribute in this direction and propose a novel adversarial defense method called Synonym Encoding Method (SEM). Specifically, SEM inserts an encoder before …
University of Kentucky（肯塔基大学）；Miami University（迈阿密大学）
Despite remarkable performance across a broad range of tasks, neural networks have been shown to be vulnerable to adversarial attacks. Many works focus on adversarial attacks and defenses on 2D images, but few focus on 3D point clouds. In this paper, our goal is to enhance the adversarial robustness of PointNet, which is one of the most widely used models for 3D point clouds. We apply the fast gradient sign attack method (FGSM) on 3D point clouds and find that FGSM can be used to generate not only adversarial images but also adversarial point clouds. To minimize the vulnerability of PointNet t…
Convolutional Neural Networks have been shown to be vulnerable to adversarial examples, which are known to locate in subspaces close to where normal data lies but are not naturally occurring and of low probability. In this work, we investigate the potential effect defense techniques have on the geometry of the likelihood landscape - likelihood of the input images under the trained model. We first propose a way to visualize the likelihood landscape leveraging an energy-based model interpretation of discriminative classifiers. Then we introduce a measure to quantify the flatness of the likelihoo…
Defense without Forgetting: Continual Adversarial Defense with Anisotropic & Isotropic Pseudo Replay
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies（广东省新型安全智能技术重点实验室）
This article presents a summary of a keynote lecture at the Deep Learning Security workshop at IEEE Security and Privacy 2018. This lecture summarizes the state of the art in defenses against adversarial examples and provides recommendations for future research directions on this topic.
The Chinese University of HongKong,Shenzhen（香港中文大学（深圳））
Deep learning models are vulnerable to adversarial examples, which poses an indisputable threat to their applications. However, recent studies observe gradient-masking defenses are self-deceiving methods if an attacker can realize this defense. In this paper, we propose a new defense method based on appending information. We introduce the Aux Block model to produce extra outputs as a self-ensemble algorithm and analytically investigate the robustness mechanism of Aux Block. We have empirically studied the efficiency of our method against adversarial examples in two types of white-box attacks, …
Recent studies on adversarial images have shown that they tend to leave the underlying low-dimensional data manifold, making them significantly more challenging for current models to make correct predictions. This so-called off-manifold conjecture has inspired a novel line of defenses against adversarial attacks on images. In this study, we find a similar phenomenon occurs in the contextualized embedding space induced by pretrained language models, in which adversarial texts tend to have their embeddings diverge from the manifold of natural ones. Based on this finding, we propose Textual Manif…
Though deep neural networks perform challenging tasks excellently, they are susceptible to adversarial examples, which mislead classifiers by applying human-imperceptible perturbations on clean inputs. Under the query-free black-box scenario, adversarial examples are hard to transfer to unknown models, and several methods have been proposed with the low transferability. To settle such issue, we design a max-min framework inspired by input transformations, which are benificial to both the adversarial attack and defense. Explicitly, we decrease loss values with inputs' affline transformations as…
University of Tübingen（图宾根大学）；DeepMind（深度思维）；Everyday Robots（日常机器人公司）
Adaptive defenses, which optimize at test time, promise to improve adversarial robustness. We categorize such adaptive test-time defenses, explain their potential benefits and drawbacks, and evaluate a representative variety of the latest adaptive defenses for image classification. Unfortunately, none significantly improve upon static defenses when subjected to our careful case study evaluation. Some even weaken the underlying static model while simultaneously increasing inference computation. While these results are disappointing, we still believe that adaptive test-time defenses are a promis…
Massachusetts Institute of Technology（麻省理工学院）；Facebook AI（Facebook人工智能）
A plethora of recent work has shown that convolutional networks are not robust to adversarial images: images that are created by perturbing a sample from the data distribution as to maximize the loss on the perturbed example. In this work, we hypothesize that adversarial perturbations move the image away from the image manifold in the sense that there exists no physical process that could have produced the adversarial image. This hypothesis suggests that a successful defense mechanism against adversarial images should aim to project the images back onto the image manifold. We study such defens…
