Adversarial training, a method for learning robust deep networks, is typically assumed to be more expensive than traditional training due to the necessity of constructing adversarial examples via a first-order method like projected gradient decent (PGD). In this paper, we make the surprising discovery that it is possible to train empirically robust models using a much weaker and cheaper adversary, an approach that was previously believed to be ineffective, rendering the method no more costly than standard training in practice. Specifically, we show that adversarial training with the fast gradient sign method (FGSM), when combined with random initialization, is as effective as PGD-based training but has significantly lower cost. Furthermore we show that FGSM adversarial training can be further accelerated by using standard techniques for efficient training of deep networks, allowing us to learn a robust CIFAR10 classifier with 45% robust accuracy to PGD attacks with $ε=8/255$ in 6 minutes, and a robust ImageNet classifier with 43% robust accuracy at $ε=2/255$ in 12 hours, in comparison to past work based on "free" adversarial training which took 10 and 50 hours to reach the same respective thresholds. Finally, we identify a failure mode referred to as "catastrophic overfitting" which may have caused previous attempts to use FGSM adversarial training to fail. All code for reproducing the experiments in this paper as well as pretrained model weights are at https://github.com/locuslab/fast_adversarial.
Nanyang Technological University（南洋理工大学）；Salesforce Research Asia（赛富时亚洲研究院）
Adversarial training has shown impressive success in learning bilingual dictionary without any parallel data by mapping monolingual embeddings to a shared space. However, recent work has shown superior performance for non-adversarial methods in more challenging language pairs. In this work, we revisit adversarial autoencoder for unsupervised word translation and propose two novel extensions to it that yield more stable training and improved results. Our method includes regularization terms to enforce cycle consistency and input reconstruction, and puts the target encoders as an adversary again…
To combat against adversarial attacks, autoencoder structure is widely used to perform denoising which is regarded as gradient masking. In this paper, we revisit the role of autoencoders in adversarial settings. Through the comprehensive experimental results and analysis, this paper presents the inherent property of adversarial robustness in the autoencoders. We also found that autoencoders may use robust features that cause inherent adversarial robustness. We believe that our discovery of the adversarial robustness of the autoencoders can provide clues to the future research and applications …
We investigate the HSIC (Hilbert-Schmidt independence criterion) bottleneck as a regularizer for learning an adversarially robust deep neural network classifier. In addition to the usual cross-entropy loss, we add regularization terms for every intermediate layer to ensure that the latent representations retain useful information for output prediction while reducing redundant information. We show that the HSIC bottleneck enhances robustness to adversarial attacks both theoretically and experimentally. In particular, we prove that the HSIC bottleneck regularizer reduces the sensitivity of the c…
École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
Despite progress in adversarial training (AT), there is a substantial gap between the top-performing and worst-performing classes in many datasets. For example, on CIFAR10, the accuracies for the best and worst classes are 74% and 23%, respectively. We argue that this gap can be reduced by explicitly optimizing for the worst-performing class, resulting in a min-max-max optimization formulation. Our method, called class focused online learning (CFOL), includes high probability convergence guarantees for the worst class loss and can be easily integrated into existing training setups with minimal…
Over the past few years, several adversarial training methods have been proposed to improve the robustness of machine learning models against adversarial perturbations in the input. Despite remarkable progress in this regard, adversarial training is often observed to drop the standard test accuracy. This phenomenon has intrigued the research community to investigate the potential tradeoff between standard accuracy (a.k.a generalization) and robust accuracy (a.k.a robust generalization) as two performance measures. In this paper, we revisit this tradeoff for latent models and argue that this tr…
Adversarial training is one effective approach for training robust deep neural networks against adversarial attacks. While being able to bring reliable robustness, adversarial training (AT) methods in general favor high capacity models, i.e., the larger the model the better the robustness. This tends to limit their effectiveness on small models, which are more preferable in scenarios where storage or computing resources are very limited (e.g., mobile devices). In this paper, we leverage the concept of knowledge distillation to improve the robustness of small models by distilling from adversari…
While adversarial training is generally used as a defense mechanism, recent works show that it can also act as a regularizer. By co-training a neural network on clean and adversarial inputs, it is possible to improve classification accuracy on the clean, non-adversarial inputs. We demonstrate that, contrary to previous findings, it is not necessary to separate batch statistics when co-training on clean and adversarial inputs, and that it is sufficient to use adapters with few domain-specific parameters for each type of input. We establish that using the classification token of a Vision Transfo…
Despite the fundamental distinction between adversarial and natural training (AT and NT), AT methods generally adopt momentum SGD (MSGD) for the outer optimization. This paper aims to analyze this choice by investigating the overlooked role of outer optimization in AT. Our exploratory evaluations reveal that AT induces higher gradient norm and variance compared to NT. This phenomenon hinders the outer optimization in AT since the convergence rate of MSGD is highly dependent on the variance of the gradients. To this end, we propose an optimization method called ENGM which regularizes the contri…
Massachusetts Institute of Technology（麻省理工学院）；Institute of Science and Technology Austria (IST Austria)（奥地利科学技术研究所（IST Austria））
Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for free but rather is accompanied by a decrease in overall model accuracy and performance. Recent work has shown that, in practical robot learning applications, the effects of adversarial training do not pose a fair trade-off but inflict a net loss when measured in holistic robot performance. This work revisits the robustness-accuracy trade-off in robot learning b…
Michigan State University（密歇根州立大学）；Sun Yat-sen University（中山大学）
Efforts to improve the adversarial robustness of convolutional neural networks have primarily focused on developing more effective adversarial training methods. In contrast, little attention was devoted to analyzing the role of architectural elements (such as topology, depth, and width) on adversarial robustness. This paper seeks to bridge this gap and present a holistic study on the impact of architectural design on adversarial robustness. We focus on residual networks and consider architecture design at the block level, i.e., topology, kernel size, activation, and normalization, as well as a…
Michigan State University（密歇根州立大学）；UC Santa Barbara（加州大学圣巴巴拉分校）；University of Minnesota（明尼苏达大学）；MIT-IBM Watson AI Lab, IBM Research（IBM研究院麻省理工-IBM沃森人工智能实验室）
Adversarial training (AT) is a widely recognized defense mechanism to gain the robustness of deep neural networks against adversarial attacks. It is built on min-max optimization (MMO), where the minimizer (i.e., defender) seeks a robust model to minimize the worst-case training loss in the presence of adversarial examples crafted by the maximizer (i.e., attacker). However, the conventional MMO method makes AT hard to scale. Thus, Fast-AT (Wong et al., 2020) and other recent algorithms attempt to simplify MMO by replacing its maximization step with the single gradient sign-based attack generat…
Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack during training to enhance its robustness. This approach, however, is computationally expensive and hence is hard to scale up. A recent work, called fast adversarial training, has shown that it is possible to markedly reduce computation time without sacrificing significant performance. This approach incorporates simple self-attacks, yet it can only run for a limi…
Recent developments in the filed of Deep Learning have demonstrated that Deep Neural Networks(DNNs) are vulnerable to adversarial examples. Specifically, in image classification, an adversarial example can fool the well trained deep neural networks by adding barely imperceptible perturbations to clean images. Adversarial Training, one of the most direct and effective methods, minimizes the losses of perturbed-data to learn robust deep networks against adversarial attacks. It has been proven that using the fast gradient sign method (FGSM) can achieve Fast Adversarial Training. However, FGSM-bas…
Deep neural networks are capable of training fast and generalizing well within many domains. Despite their promising performance, deep networks have shown sensitivities to perturbations of their inputs (e.g., adversarial examples) and their learned feature representations are often difficult to interpret, raising concerns about their true capability and trustworthiness. Recent work in adversarial training, a form of robust optimization in which the model is optimized against adversarial examples, demonstrates the ability to improve performance sensitivities to perturbations and yield feature r…
University of Waterloo（滑铁卢大学）；Vector Institute（向量研究所）
Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to "small, imperceptible" perturbations known as adversarial attacks. While the majority of existing attacks focus on measuring perturbations under the $\ell_p$ metric, Wasserstein distance, which takes geometry in pixel space into account, has long been known to be a suitable metric for measuring image quality and has recently risen as a compelling alternative to the $\ell_p$ metric in adversarial attacks. However, constructing an effective attack under the Wasserstein metric is computationally much more cha…
Hangzhou Innovation Institute, Beihang University（北京航空航天大学杭州创新研究院）；Beihang University（北京航空航天大学）；University of Ottawa（渥太华大学）
Recent researches have suggested that the predictive accuracy of neural network may contend with its adversarial robustness. This presents challenges in designing effective regularization schemes that also provide strong adversarial robustness. Revisiting Vicinal Risk Minimization (VRM) as a unifying regularization principle, we propose Adversarial Labelling of Perturbed Samples (ALPS) as a regularization scheme that aims at improving the generalization ability and adversarial robustness of the trained model. ALPS trains neural networks with synthetic samples formed by perturbing each authenti…
Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations and achieve high standard test accuracy. However, this is contrary to the standard notion that on tasks such as image classification, humans are robust classifiers with low error rate. In this work, we show that the main reason behind this confusion is the inexact definition of adversarial perturbation that is used in the literature. To fix this issue, we p…
While multi-step adversarial training is widely popular as an effective defense method against strong adversarial attacks, its computational cost is notoriously expensive, compared to standard training. Several single-step adversarial training methods have been proposed to mitigate the above-mentioned overhead cost; however, their performance is not sufficiently reliable depending on the optimization setting. To overcome such limitations, we deviate from the existing input-space-based adversarial training regime and propose a single-step latent adversarial training method (SLAT), which leverag…
Norwegian University of Science and Technology（挪威科技大学）
Despite the recent success of artificial neural networks, more biologically plausible learning methods may be needed to resolve the weaknesses of backpropagation trained models such as catastrophic forgetting and adversarial attacks. Although these weaknesses are not specifically addressed, a novel local learning rule is presented that performs online clustering with an upper limit on the number of clusters to be found rather than a fixed cluster count. Instead of using orthogonal weight or output activation constraints, activation sparsity is achieved by mutual repulsion of lateral Gaussian n…
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；Computer Science Department, University of California, Los Angeles（加州大学洛杉矶分校计算机科学系）
Adversarial training is the most empirically successful approach in improving the robustness of deep neural networks for image classification.For text classification, however, existing synonym substitution based adversarial attacks are effective but not efficient to be incorporated into practical text adversarial training. Gradient-based attacks, which are very efficient for images, are hard to be implemented for synonym substitution based text attacks due to the lexical, grammatical and semantic constraints and the discrete text input space. Thereby, we propose a fast text adversarial attack …
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Tencent Inc.（腾讯公司）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Sun Yat-sen University（中山大学）
Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating gradients at multiple steps in generating adversarial examples. To boost training efficiency, fast gradient sign method (FGSM) is adopted in fast AT methods by calculating gradient only once. Unfortunately, the robustness is far from satisfactory. One reason may arise from the initialization fashion. Existing fast AT generally uses a random sample-agnostic init…
The evaluation of robustness against adversarial manipulation of neural networks-based classifiers is mainly tested with empirical attacks as methods for the exact computation, even when available, do not scale to large networks. We propose in this paper a new white-box adversarial attack wrt the $l_p$-norms for $p \in \{1,2,\infty\}$ aiming at finding the minimal perturbation necessary to change the class of a given input. It has an intuitive geometric meaning, yields quickly high quality results, minimizes the size of the perturbation (so that it returns the robust accuracy at every threshol…
The Hong Kong University of Science and Technology（香港科技大学）；Tencent AI Lab（腾讯人工智能实验室）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent works to accelerate adversarial training is to substitute multi-step attacks (e.g., PGD) with single-step attacks (e.g., FGSM). However, these single-step methods suffer from catastrophic overfitting, where the accuracy against PGD attack suddenly drops to nearly 0% during training, destroying the robustness of the networks. In this work, we study the…
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…
With the excellent accuracy and feasibility, the Neural Networks have been widely applied into the novel intelligent applications and systems. However, with the appearance of the Adversarial Attack, the NN based system performance becomes extremely vulnerable:the image classification results can be arbitrarily misled by the adversarial examples, which are crafted images with human unperceivable pixel-level perturbation. As this raised a significant system security issue, we implemented a series of investigations on the adversarial attack in this work: We first identify an image's pixel vulnera…
Rutgers University（罗格斯大学）；The University of Tennessee, Knoxville（田纳西大学诺克斯维尔分校）
Recently, the vulnerability of DNN-based audio systems to adversarial attacks has obtained the increasing attention. However, the existing audio adversarial attacks allow the adversary to possess the entire user's audio input as well as granting sufficient time budget to generate the adversarial perturbations. These idealized assumptions, however, makes the existing audio adversarial attacks mostly impossible to be launched in a timely fashion in practice (e.g., playing unnoticeable adversarial perturbations along with user's streaming input). To overcome these limitations, in this paper we pr…
The Chinese University of Hong Kong（香港中文大学）；The University of Melbourne（墨尔本大学）；RIKEN-AIP（理化学研究所人工智能研究中心）；Hong Kong Baptist University（香港浸会大学）
The AutoAttack (AA) has been the most reliable method to evaluate adversarial robustness when considerable computational resources are available. However, the high computational cost (e.g., 100 times more than that of the project gradient descent attack) makes AA infeasible for practitioners with limited computational resources, and also hinders applications of AA in the adversarial training (AT). In this paper, we propose a novel method, minimum-margin (MM) attack, to fast and reliably evaluate adversarial robustness. Compared with AA, our method achieves comparable performance but only costs…
Northeastern University（东北大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）
Deep neural networks (DNNs) are sensitive to adversarial examples, resulting in fragile and unreliable performance in the real world. Although adversarial training (AT) is currently one of the most effective methodologies to robustify DNNs, it is computationally very expensive (e.g., 5-10X costlier than standard training). To address this challenge, existing approaches focus on single-step AT, referred to as Fast AT, reducing the overhead of adversarial example generation. Unfortunately, these approaches are known to fail against stronger adversaries. To make AT computationally efficient witho…
Tsinghua University（清华大学）；University of Southern California（南加州大学）
Deep neural networks (DNNs) significantly improved the accuracy of optical character recognition (OCR) and inspired many important applications. Unfortunately, OCRs also inherit the vulnerabilities of DNNs under adversarial examples. Different from colorful vanilla images, text images usually have clear backgrounds. Adversarial examples generated by most existing adversarial attacks are unnatural and pollute the background severely. To address this issue, we propose the Fast Adversarial Watermark Attack (FAWA) against sequence-based OCR models in the white-box manner. By disguising the perturb…
A necessary characteristic for the deployment of deep learning models in real world applications is resistance to small adversarial perturbations while maintaining accuracy on non-malicious inputs. While robust training provides models that exhibit better adversarial accuracy than standard models, there is still a significant gap in natural accuracy between robust and non-robust models which we aim to bridge. We consider a number of ensemble methods designed to mitigate this performance difference. Our key insight is that model trained to withstand small attacks, when ensembled, can often with…
Politecnico di Torino（都灵理工大学）；Technische Universität Wien (TU Wien)（维也纳工业大学（维也纳技术大学））；New York University Abu Dhabi（纽约大学阿布扎比分校）
Adversarial training is exploited to develop a robust Deep Neural Network (DNN) model against the malicious altered data. These attacks may have catastrophic effects on DNN models but are indistinguishable for a human being. For example, an external attack can modify an image adding noises invisible for a human eye, but a DNN model misclassified the image. A key objective for developing robust DNN models is to use a learning algorithm that is fast but can also give model that is robust against different types of adversarial attacks. Especially for adversarial training, enormously long training…
University of Cagliari（卡利亚里大学）；Pluribus One；Tübingen AI Center（图宾根人工智能中心）；University of Tübingen（图宾根大学）
Evaluating adversarial robustness amounts to finding the minimum perturbation needed to have an input sample misclassified. The inherent complexity of the underlying optimization requires current gradient-based attacks to be carefully tuned, initialized, and possibly executed for many computationally-demanding iterations, even if specialized to a given perturbation model. In this work, we overcome these limitations by proposing a fast minimum-norm (FMN) attack that works with different $\ell_p$-norm perturbation models ($p=0, 1, 2, \infty$), is robust to hyperparameter choices, does not requir…
University of Oxford（牛津大学）；Microsoft Research（微软研究院）
Sample efficiency is crucial for imitation learning methods to be applicable in real-world applications. Many studies improve sample efficiency by extending adversarial imitation to be off-policy regardless of the fact that these off-policy extensions could either change the original objective or involve complicated optimization. We revisit the foundation of adversarial imitation and propose an off-policy sample efficient approach that requires no adversarial training or min-max optimization. Our formulation capitalizes on two key insights: (1) the similarity between the Bellman equation and t…
Inria（法国国家信息与自动化研究所）；CNRS（法国国家科学研究中心）；IRISA（法国雷恩信息系统与随机系统研究所）；Univ Rennes（雷恩大学）；East China Normal University（华东师范大学）
Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks in our everyday lives. When white-box attacks are almost always successful, it is typically only the distortion of the perturbations that matters in their evaluation. In this work, we argue that speed is important as well, especially when considering that fast attacks are required by adversarial training. Given more time, iterative methods can always find bet…
Although fast adversarial training provides an efficient approach for building robust networks, it may suffer from a serious problem known as catastrophic overfitting (CO), where multi-step robust accuracy suddenly collapses to zero. In this paper, we for the first time decouple single-step adversarial examples into data-information and self-information, which reveals an interesting phenomenon called "self-fitting". Self-fitting, i.e., the network learns the self-information embedded in single-step perturbations, naturally leads to the occurrence of CO. When self-fitting occurs, the network ex…
Dalian University of Technology（大连理工大学）；Harbin Institute of Technology（哈尔滨工业大学）；JD Explore Academy（京东探索研究院）
Physics-informed neural networks (PINNs) provide a deep learning framework for numerically solving partial differential equations (PDEs), and have been widely used in a variety of PDE problems. However, there still remain some challenges in the application of PINNs: 1) the mechanism of PINNs is unsuitable (at least cannot be directly applied) to exploiting a small size of (usually very few) extra informative samples to refine the networks; and 2) the efficiency of training PINNs often becomes low for some complicated PDEs. In this paper, we propose the generative adversarial physics-informed n…
Security-sensitive applications that rely on Deep Neural Networks (DNNs) are vulnerable to small perturbations that are crafted to generate Adversarial Examples(AEs). The AEs are imperceptible to humans and cause DNN to misclassify them. Many defense and detection techniques have been proposed. Model's confidences and Dropout, as a popular way to estimate the model's uncertainty, have been used for AE detection but they showed limited success against black- and gray-box attacks. Moreover, the state-of-the-art detection techniques have been designed for specific attacks or broken by others, nee…
Revisiting Adversarial Attacks on Graph Neural Networks for Graph Classification
Tsinghua University（清华大学）；Tsinghua-Berkeley Shenzhen Institute, Tsinghua University（清华大学清华-伯克利深圳学院）；Chinese University of Hong Kong（香港中文大学）；Ant Group（蚂蚁集团）
Most recent studies on neural constituency parsing focus on encoder structures, while few developments are devoted to decoders. Previous research has demonstrated that probabilistic statistical methods based on syntactic rules are particularly effective in constituency parsing, whereas syntactic rules are not used during the training of neural models in prior work probably due to their enormous computation requirements. In this paper, we first implement a fast CKY decoding procedure harnessing GPU acceleration, based on which we further derive a syntactic rule-based (rule-constrained) CKY deco…
University of Michigan, Ann Arbor（密歇根大学安娜堡分校）；Georgia Institute of Technology（佐治亚理工学院）
We revisit the Frank-Wolfe (FW) optimization under strongly convex constraint sets. We provide a faster convergence rate for FW without line search, showing that a previously overlooked variant of FW is indeed faster than the standard variant. With line search, we show that FW can converge to the global optimum, even for smooth functions that are not convex, but are quasi-convex and locally-Lipschitz. We also show that, for the general case of (smooth) non-convex functions, FW with line search converges with high probability to a stationary point at a rate of $O\left(\frac{1}{t}\right)$, as lo…
University of California Santa Barbara（加州大学圣巴巴拉分校）；University of California, San Diego（加州大学圣地亚哥分校）
The Private Aggregation of Teacher Ensembles (PATE) framework is one of the most promising recent approaches in differentially private learning. Existing theoretical analysis shows that PATE consistently learns any VC-classes in the realizable setting, but falls short in explaining its success in more general cases where the error rate of the optimal classifier is bounded away from zero. We fill in this gap by introducing the Tsybakov Noise Condition (TNC) and establish stronger and more interpretable learning bounds. These bounds provide new insights into when PATE works and improve over exis…
University of Arizona（亚利桑那大学）；Amii（阿尔伯塔机器智能研究所）；University of Alberta（阿尔伯塔大学）；DeepMind（深度思维）
Simple regret is a natural and parameter-free performance criterion for pure exploration in multi-armed bandits yet is less popular than the probability of missing the best arm or an $ε$-good arm, perhaps due to lack of easy ways to characterize it. In this paper, we make significant progress on minimizing simple regret in both data-rich ($T\ge n$) and data-poor regime ($T \le n$) where $n$ is the number of arms, and $T$ is the number of samples. At its heart is our improved instance-dependent analysis of the well-known Sequential Halving (SH) algorithm, where we bound the probability of retur…
College of William and Mary（威廉与玛丽学院）；IBM Research（IBM研究院）；Baidu Inc.（百度公司）
Kernel method has been developed as one of the standard approaches for nonlinear learning, which however, does not scale to large data set due to its quadratic complexity in the number of samples. A number of kernel approximation methods have thus been proposed in the recent years, among which the random features method gains much popularity due to its simplicity and direct reduction of nonlinear problem to a linear one. The Random Binning (RB) feature, proposed in the first random-feature paper \cite{rahimi2007random}, has drawn much less attention than the Random Fourier (RF) feature. In thi…
The proper initialization of weights is crucial for the effective training and fast convergence of deep neural networks (DNNs). Prior work in this area has mostly focused on balancing the variance among weights per layer to maintain stability of (i) the input data propagated forwards through the network and (ii) the loss gradients propagated backwards, respectively. This prevalent heuristic is however agnostic of dependencies among gradients across the various layers and captures only firstorder effects. In this paper, we propose and discuss an initialization principle that is based on a rigor…
