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 phenomenon from the perspective of training instances. We show that catastrophic overfitting is instance-dependent and fitting instances with larger gradient norm is more likely to cause catastrophic overfitting. Based on our findings, we propose a simple but effective method, Adversarial Training with Adaptive Step size (ATAS). ATAS learns an instancewise adaptive step size that is inversely proportional to its gradient norm. The theoretical analysis shows that ATAS converges faster than the commonly adopted non-adaptive counterparts. Empirically, ATAS consistently mitigates catastrophic overfitting and achieves higher robust accuracy on CIFAR10, CIFAR100 and ImageNet when evaluated on various adversarial budgets.
Adversarial training is a method for enhancing neural networks to improve the robustness against adversarial examples. Besides the security concerns of potential adversarial examples, adversarial training can also improve the generalization ability of neural networks, train robust neural networks, and provide interpretability for neural networks. In this work, we introduce adversarial training in time series analysis to enhance the neural networks for better generalization ability by taking the finance field as an example. Rethinking existing research on adversarial training, we propose the ad…
Swansea University（斯旺西大学）；Université de Toulon（土伦大学）；Aix Marseille Univ（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）
Deep Neural Networks (DNNs) have often supplied state-of-the-art results in pattern recognition tasks. Despite their advances, however, the existence of adversarial examples have caught the attention of the community. Many existing works have proposed methods for searching for adversarial examples within fixed-sized regions around training points. Our work complements and improves these existing approaches by adapting the size of these regions based on the problem complexity and data sampling density. This makes such approaches more appropriate for other types of data and may further improve a…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Tencent AI Lab（腾讯AI实验室）；Shenzhen Research Institute of Big Data（深圳大数据研究院）
Adversarial Training (AT) has been demonstrated as one of the most effective methods against adversarial examples. While most existing works focus on AT with a single type of perturbation e.g., the $\ell_\infty$ attacks), DNNs are facing threats from different types of adversarial examples. Therefore, adversarial training for multiple perturbations (ATMP) is proposed to generalize the adversarial robustness over different perturbation types (in $\ell_1$, $\ell_2$, and $\ell_\infty$ norm-bounded perturbations). However, the resulting model exhibits trade-off between different attacks. Meanwhile…
Adversarial training has proven to be effective in hardening networks against adversarial examples. However, the gained robustness is limited by network capacity and number of training samples. Consequently, to build more robust models, it is common practice to train on widened networks with more parameters. To boost robustness, we propose a conditional normalization module to adapt networks when conditioned on input samples. Our adaptive networks, once adversarially trained, can outperform their non-adaptive counterparts on both clean validation accuracy and robustness. Our method is objectiv…
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…
Institute Intelligence and Data (IID), Université Laval（拉瓦尔大学智能与数据研究所（IID））；Mila（米拉研究所）
Neural network ensembles have been studied extensively in the context of adversarial robustness and most ensemble-based approaches remain vulnerable to adaptive attacks. In this paper, we investigate the robustness of Error-Correcting Output Codes (ECOC) ensembles through architectural improvements and ensemble diversity promotion. We perform a comprehensive robustness assessment against adaptive attacks and investigate the relationship between ensemble diversity and robustness. Our results demonstrate the benefits of ECOC ensembles for adversarial robustness compared to regular ensembles of c…
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. In this paper we study how the choice of optimization algorithm influences the robustness of the resulting classifier to adversarial examples. Specifically we show an example of a learning problem for which the solution found by adaptive optimization algorithms exhibits qualitatively worse robustness properties against both $L_{2}$- and $L_{\infty}$-adversaries than the solution found by non-a…
Beijing Jiaotong University（北京交通大学）；University of Science and Technology of China（中国科学技术大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Adversarial examples provide an opportunity as well as impose a challenge for understanding image classification systems. Based on the analysis of the adversarial training solution Adversarial Logits Pairing (ALP), we observed in this work that: (1) The inference of adversarially robust model tends to rely on fewer high-contribution features compared with vulnerable ones. (2) The training target of ALP doesn't fit well to a noticeable part of samples, where the logits pairing loss is overemphasized and obstructs minimizing the classification loss. Motivated by these observations, we design an …
The University of Sydney（悉尼大学）；Xidian University（西安电子科技大学）；JD Explore Academy（京东探索研究院）；University of Science and Technology of China（中国科学技术大学）；Hong Kong Baptist University（香港浸会大学）；The University of Melbourne（墨尔本大学）
Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a pre-specified perturbation budget on networks of various model capacities will yield divergent degree of robustness disparity between natural and robust accuracies, which deviates from robust network's desideratum. Secondly, the attack strength of adversarial training data constrained by the pre-specified perturbation budget fails to upgrade as the growth of network r…
School of Computing, University of Singapore（新加坡大学计算学院）
Adversarial training, the process of training a deep learning model with adversarial data, is one of the most successful adversarial defense methods for deep learning models. We have found that the robustness to white-box attack of an adversarially trained model can be further improved if we fine tune this model in inference stage to adapt to the adversarial input, with the extra information in it. We introduce an algorithm that "post trains" the model at inference stage between the original output class and a "neighbor" class, with existing training data. The accuracy of pre-trained Fast-FGSM…
Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense against such adversarial attacks. This work focuses on improving adversarial training to boost adversarial robustness. We first analyze, from an instance-wise perspective, how adversarial vulnerability evolves during adversarial training. We find that during training an overall reduction of adversarial loss is achieved by sacrificing a considerable proporti…
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…
Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
Sichuan University（四川大学）；Dongfang Electric (Chengdu) Innovation Research Co., Ltd.（东方电子（成都）创新研究院有限公司）；Southwest China Research Institute of Electronic Equipment（西南中国电子设备研究院）
Facebook AI Research（Facebook人工智能研究院）；University of Maryland（马里兰大学）；Georgia Institute of Technology（佐治亚理工学院）
Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test set. We hypothesize that this poor generalization is a consequence of adversarial training with uniform perturbation radius around every training sample. Samples close to decision boundary can be morphed into a different class under a small perturbation budget, and enforcing large margins around these samples produce poor decision boundaries that generalize po…
University of Florida（佛罗里达大学）；Tongdun Technology（同盾科技）
Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks (e.g., C&W attack) require manually tuning hyper-parameters and take a long time to construct an adversarial example, making it impractical to attack real-time systems; (ii) Most of the studies focus on non-sequential tasks, such as image classification, yet only a few consider sequential tasks. In this work, we speed up adversarial attacks, especially on seque…
Department of Computer Science, University of Oxford（牛津大学计算机科学系（注：这里按要求提取到大学级别，实际机构是牛津大学，其下的计算机科学系作为所属机构））
Neural networks are vulnerable to adversarially-constructed perturbations of their inputs. Most research so far has considered perturbations of a fixed magnitude under some $l_p$ norm. Although studying these attacks is valuable, there has been increasing interest in the construction of (and robustness to) unrestricted attacks, which are not constrained to a small and rather artificial subset of all possible adversarial inputs. We introduce a novel algorithm for generating such unrestricted adversarial inputs which, unlike prior work, is adaptive: it is able to tune its attacks to the classifi…
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…
University of California at Berkeley（加州大学伯克利分校）；University of California at San Diego（加州大学圣地亚哥分校）
Generative Adversarial Networks (GANs) are a class of generative models used for various applications, but they have been known to suffer from the mode collapse problem, in which some modes of the target distribution are ignored by the generator. Investigative study using a new data generation procedure indicates that the mode collapse of the generator is driven by the discriminator's inability to maintain classification accuracy on previously seen samples, a phenomenon called Catastrophic Forgetting in continual learning. Motivated by this observation, we introduce a novel training procedure …
The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an adaptive view of the issue via evaluating various test-time smoothing defense against white-box untargeted adversarial examples. Through controlled experiments with pretrained ResNet-152 on ImageNet, we first illustrate the non-monotonic relation between adversarial attacks and smoothing defenses. Then at the dataset level, we observe large variance among samples …
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 …
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…
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…
It is known that Deep Neural networks (DNNs) are vulnerable to adversarial attacks, and the adversarial robustness of DNNs could be improved by adding adversarial noises to training data (e.g., the standard adversarial training (SAT)). However, inappropriate noises added to training data may reduce a model's performance, which is termed the trade-off between accuracy and robustness. This problem has been sufficiently studied for the classification of whole images but has rarely been explored for image analysis tasks in the medical application domain, including image segmentation, landmark dete…
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 Michigan（密歇根大学）；University of California, Irvine（加利福尼亚大学尔湾分校）
3D point clouds play pivotal roles in various safety-critical applications, such as autonomous driving, which desires the underlying deep neural networks to be robust to adversarial perturbations. Though a few defenses against adversarial point cloud classification have been proposed, it remains unknown whether they are truly robust to adaptive attacks. To this end, we perform the first security analysis of state-of-the-art defenses and design adaptive evaluations on them. Our 100% adaptive attack success rates show that current countermeasures are still vulnerable. Since adversarial training …
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…
The phenomenon of adversarial examples in deep learning models has caused substantial concern over their reliability. While many deep neural networks have shown impressive performance in terms of predictive accuracy, it has been shown that in many instances an imperceptible perturbation can falsely flip the network's prediction. Most research has then focused on developing defenses against adversarial attacks or learning under a worst-case adversarial loss. In this work, we take a step back and aim to provide a framework for determining whether a model's label change under small perturbation i…
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…
George Mason University（乔治梅森大学）；Drexel University（德雷塞尔大学）；University of California, Davis（加州大学戴维斯分校）
This paper presents a novel model training solution, denoted as Adaptive-Gravity, for enhancing the robustness of deep neural network classifiers against adversarial examples. We conceptualize the model parameters/features associated with each class as a mass characterized by its centroid location and the spread (standard deviation of the distance) of features around the centroid. We use the centroid associated with each cluster to derive an anti-gravity force that pushes the centroids of different classes away from one another during network training. Then we customized an objective function …
UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems
Department of Computer Science, City University of Hong Kong（城市大学计算机科学系）；School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区信息科学与技术学院）
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 gradi…
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…
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…
Indian Institute of Technology Kharagpur（印度理工学院卡拉格布尔分校）
With the rapid advancement and increased use of deep learning models in image identification, security becomes a major concern to their deployment in safety-critical systems. Since the accuracy and robustness of deep learning models are primarily attributed from the purity of the training samples, therefore the deep learning architectures are often susceptible to adversarial attacks. Adversarial attacks are often obtained by making subtle perturbations to normal images, which are mostly imperceptible to humans, but can seriously confuse the state-of-the-art machine learning models. We propose …
Towards Reliable Evaluation of Adversarial Robustness for Spiking Neural Networks
Brain-inspired Cognitive AI Lab, Institute of Automation, Chinese Academy of Sciences（脑启发认知人工智能实验室，自动化研究所，中国科学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）；Beijing Institute of AI Safety and Governance（北京人工智能安全与治理研究院）；Beijing Key Laboratory of Safe Al and Superalignment（北京安全人工智能与超对齐重点实验室）；Center for Long-term AI（长期人工智能中心）
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…
Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification
College of Information Science and Engineering, Northeastern University（东北大学信息科学与工程学院）；Foshan Graduate School, Northeastern University（东北大学佛山研究生院）；Faculty of Robot Science and Engineering, Northeastern University（东北大学机器人科学与工程学院）；State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University（东北大学流程工业综合自动化国家重点实验室）；School of Intelligent Systems Engineering, Sun Yat-Sen University（中山大学智能系统工程学院）；Guangdong Provincial Key Laboratory of Fire Science and Technology（广东省火灾科学与技术重点实验室）
School of Computer Science & Technology, HUST（华中科技大学计算机科学与技术学院）；CAI, UTS（悉尼科技大学人工智能中心）
For unsupervised domain adaptation problems, the strategy of aligning the two domains in latent feature space through adversarial learning has achieved much progress in image classification, but usually fails in semantic segmentation tasks in which the latent representations are overcomplex. In this work, we equip the adversarial network with a "significance-aware information bottleneck (SIB)", to address the above problem. The new network structure, called SIBAN, enables a significance-aware feature purification before the adversarial adaptation, which eases the feature alignment and stabiliz…
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…
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…
