We first elucidate various fundamental properties of optimal adversarial predictors: the structure of optimal adversarial convex predictors in terms of optimal adversarial zero-one predictors, bounds relating the adversarial convex loss to the adversarial zero-one loss, and the fact that continuous predictors can get arbitrarily close to the optimal adversarial error for both convex and zero-one losses. Applying these results along with new Rademacher complexity bounds for adversarial training near initialization, we prove that for general data distributions and perturbation sets, adversarial training on shallow networks with early stopping and an idealized optimal adversary is able to achieve optimal adversarial test error. By contrast, prior theoretical work either considered specialized data distributions or only provided training error guarantees.
Network pruning has been known to produce compact models without much accuracy degradation. However, how the pruning process affects a network's robustness and the working mechanism behind remain unresolved. In this work, we theoretically prove that the sparsity of network weights is closely associated with model robustness. Through experiments on a variety of adversarial pruning methods, we find that weights sparsity will not hurt but improve robustness, where both weights inheritance from the lottery ticket and adversarial training improve model robustness in network pruning. Based on these …
Montreal Institute for Learning Algorithms (MILA)（蒙特利尔学习算法研究所（MILA））；Aalto University（阿尔托大学）；Harvard University（哈佛大学）；National University of Singapore（新加坡国立大学）；Google（谷歌）
Adversarial robustness has become a central goal in deep learning, both in the theory and the practice. However, successful methods to improve the adversarial robustness (such as adversarial training) greatly hurt generalization performance on the unperturbed data. This could have a major impact on how the adversarial robustness affects real world systems (i.e. many may opt to forego robustness if it can improve accuracy on the unperturbed data). We propose Interpolated Adversarial Training, which employs recently proposed interpolation based training methods in the framework of adversarial tr…
A new understanding of adversarial examples and adversarial robustness is proposed by decoupling the data generator and the label generator (which we call the teacher). In our framework, adversarial robustness is a conditional concept---the student model is not absolutely robust, but robust with respect to the teacher. Based on the new understanding, we claim that adversarial examples exist because the student cannot obtain sufficient information of the teacher from the training data. Various ways of achieving robustness is compared. Theoretical and numerical evidence shows that to efficiently…
Georgia Institute of Technology（佐治亚理工学院）；Google Research（谷歌研究院）
Alongside the well-publicized accomplishments of deep neural networks there has emerged an apparent bug in their success on tasks such as object recognition: with deep models trained using vanilla methods, input images can be slightly corrupted in order to modify output predictions, even when these corruptions are practically invisible. This apparent lack of robustness has led researchers to propose methods that can help to prevent an adversary from having such capabilities. The state-of-the-art approaches have incorporated the robustness requirement into the loss function, and the training pr…
Nankai University（南开大学）；Tencent（腾讯）；National University of Singapore（新加坡国立大学）
The vulnerability to slight input perturbations is a worrying yet intriguing property of deep neural networks (DNNs). Despite many previous works studying the reason behind such adversarial behavior, the relationship between the generalization performance and adversarial behavior of DNNs is still little understood. In this work, we reveal such relation by introducing a metric characterizing the generalization performance of a DNN. The metric can be disentangled into an information-theoretic non-robust component, responsible for adversarial behavior, and a robust component. Then, we show by exp…
As humans, we inherently perceive images based on their predominant features, and ignore noise embedded within lower bit planes. On the contrary, Deep Neural Networks are known to confidently misclassify images corrupted with meticulously crafted perturbations that are nearly imperceptible to the human eye. In this work, we attempt to address this problem by training networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction. We demonstrate that, by imposing consistency on the representations learned across di…
We study the design of computationally efficient algorithms with provable guarantees, that are robust to adversarial (test time) perturbations. While there has been an proliferation of recent work on this topic due to its connections to test time robustness of deep networks, there is limited theoretical understanding of several basic questions like (i) when and how can one design provably robust learning algorithms? (ii) what is the price of achieving robustness to adversarial examples in a computationally efficient manner? The main contribution of this work is to exhibit a strong connection b…
Toyota Technological Institute at Chicago（芝加哥丰田技术研究院）；Purdue University（普渡大学）
We present a minimax optimal learner for the problem of learning predictors robust to adversarial examples at test-time. Interestingly, we find that this requires new algorithmic ideas and approaches to adversarially robust learning. In particular, we show, in a strong negative sense, the suboptimality of the robust learner proposed by Montasser, Hanneke, and Srebro (2019) and a broader family of learners we identify as local learners. Our results are enabled by adopting a global perspective, specifically, through a key technical contribution: the global one-inclusion graph, which may be of in…
Recent research has made the surprising finding that state-of-the-art deep learning models sometimes fail to generalize to small variations of the input. Adversarial training has been shown to be an effective approach to overcome this problem. However, its application has been limited to enforcing invariance to analytically defined transformations like $\ell_p$-norm bounded perturbations. Such perturbations do not necessarily cover plausible real-world variations that preserve the semantics of the input (such as a change in lighting conditions). In this paper, we propose a novel approach to ex…
Tel-Aviv University（特拉维夫大学）；The Allen Institute for AI（艾伦人工智能研究所）
Discrete adversarial attacks are symbolic perturbations to a language input that preserve the output label but lead to a prediction error. While such attacks have been extensively explored for the purpose of evaluating model robustness, their utility for improving robustness has been limited to offline augmentation only. Concretely, given a trained model, attacks are used to generate perturbed (adversarial) examples, and the model is re-trained exactly once. In this work, we address this gap and leverage discrete attacks for online augmentation, where adversarial examples are generated at ever…
IRIT；Université Paul Sabatier Toulouse（图卢兹第三大学）；IRT Saint-Exupery（圣埃克苏佩里技术研究院）；IMT；Universidad de Valladolid（巴利亚多利德大学）
Adversarial examples have pointed out Deep Neural Networks vulnerability to small local noise. It has been shown that constraining their Lipschitz constant should enhance robustness, but make them harder to learn with classical loss functions. We propose a new framework for binary classification, based on optimal transport, which integrates this Lipschitz constraint as a theoretical requirement. We propose to learn 1-Lipschitz networks using a new loss that is an hinge regularized version of the Kantorovich-Rubinstein dual formulation for the Wasserstein distance estimation. This loss function…
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）
We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism. We show that the forgetting mechanism serves as an information-bottleneck, which is manipulated by the adversarial training to learn invariance to unwanted factors. Empirical results show that the proposed framework achieves state-of-the-art performance at learning invariance in both nuisance and bias settings on a diverse collection of datasets and tasks.
We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by the mutual information between the degraded signal and the label of interest. This problem is motivated by the existence of adversarial examples for machine learning classifiers. By adopting an information theoretic perspective, we seek to identify conditions under which adversarial vulnerability is unavoidable i.e. even optimally designed classifiers will be vulnerable to small adversarial perturbations. We present …
Convolutional neural networks (CNNs) are known for their good performance and generalization in vision-related tasks and have become state-of-the-art in both application and research-based domains. However, just like other neural network models, they suffer from a susceptibility to noise and adversarial attacks. An adversarial defence aims at reducing a neural network's susceptibility to adversarial attacks through learning or architectural modifications. We propose the weight map layer (WM) as a generic architectural addition to CNNs and show that it can increase their robustness to noise and…
Here we propose a general theoretical method for analyzing the risk bound in the presence of adversaries. Specifically, we try to fit the adversarial learning problem into the minimax framework. We first show that the original adversarial learning problem can be reduced to a minimax statistical learning problem by introducing a transport map between distributions. Then, we prove a new risk bound for this minimax problem in terms of covering numbers under a weak version of Lipschitz condition. Our method can be applied to multi-class classification problems and commonly used loss functions such…
Optimal Transport Regularized Divergences: Application to Adversarial Robustness
Department of Mathematics（数学系）；Texas State University（德克萨斯州立大学）；School of Information Systems and Management（信息系统与管理学院）；University of South Florida（佛罗里达州立大学）
Adversarial robustness has become a fundamental requirement in modern machine learning applications. Yet, there has been surprisingly little statistical understanding so far. In this paper, we provide the first result of the optimal minimax guarantees for the excess risk for adversarially robust classification, under Gaussian mixture model proposed by \cite{schmidt2018adversarially}. The results are stated in terms of the Adversarial Signal-to-Noise Ratio (AdvSNR), which generalizes a similar notion for standard linear classification to the adversarial setting. For the Gaussian mixtures with A…
Deep learning classifiers are now known to have flaws in the representations of their class. Adversarial attacks can find a human-imperceptible perturbation for a given image that will mislead a trained model. The most effective methods to defend against such attacks trains on generated adversarial examples to learn their distribution. Previous work aimed to align original and adversarial image representations in the same way as domain adaptation to improve robustness. Yet, they partially align the representations using approaches that do not reflect the geometry of space and distribution. In …
The fragility of deep neural networks to adversarially-chosen inputs has motivated the need to revisit deep learning algorithms. Including adversarial examples during training is a popular defense mechanism against adversarial attacks. This mechanism can be formulated as a min-max optimization problem, where the adversary seeks to maximize the loss function using an iterative first-order algorithm while the learner attempts to minimize it. However, finding adversarial examples in this way causes excessive computational overhead during training. By interpreting the min-max problem as an optimal…
Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Adversarial deep learning is to train robust DNNs against adversarial attacks, which is one of the major research focuses of deep learning. Game theory has been used to answer some of the basic questions about adversarial deep learning such as the existence of a classifier with optimal robustness and the existence of optimal adversarial samples for a given class of classifiers. In most previous work, adversarial deep learning was formulated as a simultaneous game and the strategy spaces are assumed to be certain probability distributions in order for the Nash equilibrium to exist. But, this as…
We theoretically analyse the limits of robustness to test-time adversarial and noisy examples in classification. Our work focuses on deriving bounds which uniformly apply to all classifiers (i.e all measurable functions from features to labels) for a given problem. Our contributions are two-fold. (1) We use optimal transport theory to derive variational formulae for the Bayes-optimal error a classifier can make on a given classification problem, subject to adversarial attacks. The optimal adversarial attack is then an optimal transport plan for a certain binary cost-function induced by the spe…
EPFL（洛桑联邦理工学院）；University College London（伦敦大学学院）；University of California, Berkeley（加州大学伯克利分校）
Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The existing literature on provable adversarial robustness of models, however, exclusively focuses on robustness to gradient-based attacks in domains such as images. These attacks model the adversarial cost, e.g., amount of distortion applied to an image, as a $p$-norm. We argue that this approach is not well-suited to model adversarial costs in constrained doma…
Neural networks are part of many contemporary NLP systems, yet their empirical successes come at the price of vulnerability to adversarial attacks. Previous work has used adversarial training and data augmentation to partially mitigate such brittleness, but these are unlikely to find worst-case adversaries due to the complexity of the search space arising from discrete text perturbations. In this work, we approach the problem from the opposite direction: to formally verify a system's robustness against a predefined class of adversarial attacks. We study text classification under synonym replac…
This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-case inputs. We then frame commonly used attacks and evaluation metrics as defining a tractable surrogate objective to the true adversarial risk. This suggests that models may optimize this surrogate rather than the true adversarial risk. We formalize this notion as 'obscurity to an adversary,' and develop tools and heuristics for identifying obscured models and designing transp…
Consider the problem of simultaneous estimation of location and variance matrix under Huber's contaminated Gaussian model. First, we study minimum $f$-divergence estimation at the population level, corresponding to a generative adversarial method with a nonparametric discriminator and establish conditions on $f$-divergences which lead to robust estimation, similarly to robustness of minimum distance estimation. More importantly, we develop tractable adversarial algorithms with simple spline discriminators, which can be implemented via nested optimization such that the discriminator parameters …
Information Technology University (ITU)-Punjab（旁遮普信息技术大学）；University of Southern Queensland（南昆士兰大学）
Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of SER systems by showing the susceptibility of deep neural networks to adversarial examples as they rely only on small and imperceptible perturbations. In this study, we evaluate how adversarial examples can be used to attack SER systems and propose the first black-box adversarial attack on SER systems. We also explore potential defenses including adversarial t…
Princeton University（普林斯顿大学）；Pennsylvania State University（宾夕法尼亚州立大学）
While progress has been made in understanding the robustness of machine learning classifiers to test-time adversaries (evasion attacks), fundamental questions remain unresolved. In this paper, we use optimal transport to characterize the minimum possible loss in an adversarial classification scenario. In this setting, an adversary receives a random labeled example from one of two classes, perturbs the example subject to a neighborhood constraint, and presents the modified example to the classifier. We define an appropriate cost function such that the minimum transportation cost between the dis…
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of Cambridge（剑桥大学）
Adversarial risk quantifies the performance of classifiers on adversarially perturbed data. Numerous definitions of adversarial risk -- not all mathematically rigorous and differing subtly in the details -- have appeared in the literature. In this paper, we revisit these definitions, make them rigorous, and critically examine their similarities and differences. Our technical tools derive from optimal transport, robust statistics, functional analysis, and game theory. Our contributions include the following: generalizing Strassen's theorem to the unbalanced optimal transport setting with applic…
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However, adversarial examples may be overfit to exploit the particular architecture and feature representation of a source model, resulting in sub-optimal black-box transfer attacks to other target models. This leads us to introduce the Intermediate Level Attack (ILA), which attempts to fine-tune an existing adversarial example for greater black-box transferability …
OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack
Shanghai Institute for Mathematics and Interdisciplinary Sciences（上海数学与交叉科学研究院）；Academy of Mathematics and Systems Science（数学系统科学学院）；University of Chinese Academy of Sciences（中国科学院大学）
University of Michigan（密歇根大学）；University of California, Davis（加利福尼亚大学戴维斯分校）
In this paper, we investigate the adversarial robustness of multivariate $M$-Estimators. In the considered model, after observing the whole dataset, an adversary can modify all data points with the goal of maximizing inference errors. We use adversarial influence function (AIF) to measure the asymptotic rate at which the adversary can change the inference result. We first characterize the adversary's optimal modification strategy and its corresponding AIF. From the defender's perspective, we would like to design an estimator that has a small AIF. For the case of joint location and scale estima…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Ecole polytechnique fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Princeton University（普林斯顿大学）
We consider a learning system based on the conventional multiplicative weight (MW) rule that combines experts' advice to predict a sequence of true outcomes. It is assumed that one of the experts is malicious and aims to impose the maximum loss on the system. The loss of the system is naturally defined to be the aggregate absolute difference between the sequence of predicted outcomes and the true outcomes. We consider this problem under both offline and online settings. In the offline setting where the malicious expert must choose its entire sequence of decisions a priori, we show somewhat sur…
In this paper, we study the adversarial robustness of subspace learning problems. Different from the assumptions made in existing work on robust subspace learning where data samples are contaminated by gross sparse outliers or small dense noises, we consider a more powerful adversary who can first observe the data matrix and then intentionally modify the whole data matrix. We first characterize the optimal rank-one attack strategy that maximizes the subspace distance between the subspace learned from the original data matrix and that learned from the modified data matrix. We then generalize th…
Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images. This security vulnerability has led to vast research in recent years because it can introduce real-world threats into systems that rely on neural networks. Yet, a deep understanding of the characteristics of adversarial examples has remained elusive. We propose a new way of achieving such understanding through a recent development, namely, invertible neural models with Lipschitz continuous mapping functions from the input to the output. With th…
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心 (DFKI)）；TU Kaiserslautern（凯泽斯劳滕工业大学）；NVIDIA Research（英伟达研究院）
In this paper, we investigate the use of pretraining with adversarial networks, with the objective of discovering the relationship between network depth and robustness. For this purpose, we selectively retrain different portions of VGG and ResNet architectures on CIFAR-10, Imagenette, and ImageNet using non-adversarial and adversarial data. Experimental results show that susceptibility to adversarial samples is associated with low-level feature extraction layers. Therefore, retraining of high-level layers is insufficient for achieving robustness. Furthermore, adversarial attacks yield outputs …
In recent years, the ML community has seen surges of interest in both adversarially robust learning and implicit layers, but connections between these two areas have seldom been explored. In this work, we combine innovations from these areas to tackle the problem of N-k security-constrained optimal power flow (SCOPF). N-k SCOPF is a core problem for the operation of electrical grids, and aims to schedule power generation in a manner that is robust to potentially k simultaneous equipment outages. Inspired by methods in adversarially robust training, we frame N-k SCOPF as a minimax optimization …
In this paper, we take a first step towards answering the question of how to design fair machine learning algorithms that are robust to adversarial attacks. Using a minimax framework, we aim to design an adversarially robust fair regression model that achieves optimal performance in the presence of an attacker who is able to add a carefully designed adversarial data point to the dataset or perform a rank-one attack on the dataset. By solving the proposed nonsmooth nonconvex-nonconcave minimax problem, the optimal adversary as well as the robust fairness-aware regression model are obtained. For…
Zhejiang University（浙江大学）；AZFT Joint Lab for Knowledge Engine（AZFT知识引擎联合实验室）；Alibaba Group（阿里巴巴集团）
Recent neural-based relation extraction approaches, though achieving promising improvement on benchmark datasets, have reported their vulnerability towards adversarial attacks. Thus far, efforts mostly focused on generating adversarial samples or defending adversarial attacks, but little is known about the difference between normal and adversarial samples. In this work, we take the first step to leverage the salience-based method to analyze those adversarial samples. We observe that salience tokens have a direct correlation with adversarial perturbations. We further find the adversarial pertur…
Image augmentations applied during training are crucial for the generalization performance of image classifiers. Therefore, a large body of research has focused on finding the optimal augmentation policy for a given task. Yet, RandAugment [2], a simple random augmentation policy, has recently been shown to outperform existing sophisticated policies. Only Adversarial AutoAugment (AdvAA) [11], an approach based on the idea of adversarial training, has shown to be better than RandAugment. In this paper, we show that random augmentations are still competitive compared to an optimal adversarial app…
Towards Optimal Randomized Strategies in Adversarial Example Game
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Advanced Technology Institute, Zhejiang University（浙江大学先进技术研究院）；Qiushi Academy for Advanced Studies, Zhejiang University（浙江大学求是高等研究院）；State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室）
Mathematical Institute for Data Science, Johns Hopkins University（约翰斯·霍普金斯大学数据科学数学研究所）
Adversarial training (AT) is a simple yet effective defense against adversarial attacks to image classification systems, which is based on augmenting the training set with attacks that maximize the loss. However, the effectiveness of AT as a defense for video classification has not been thoroughly studied. Our first contribution is to show that generating optimal attacks for video requires carefully tuning the attack parameters, especially the step size. Notably, we show that the optimal step size varies linearly with the attack budget. Our second contribution is to show that using a smaller (…
Machine Learning models have been shown to be vulnerable to adversarial examples, ie. the manipulation of data by a attacker to defeat a defender's classifier at test time. We present a novel probabilistic definition of adversarial examples in perfect or limited knowledge setting using prior probability distributions on the defender's classifier. Using the asymptotic properties of the logistic regression, we derive a closed-form expression of the intensity of any adversarial perturbation, in order to achieve a given expected misclassification rate. This technique is relevant in a threat model …
Motivated by recent data analytics applications, we study the adversarial robustness of robust estimators. Instead of assuming that only a fraction of the data points are outliers as considered in the classic robust estimation setup, in this paper, we consider an adversarial setup in which an attacker can observe the whole dataset and can modify all data samples in an adversarial manner so as to maximize the estimation error caused by his attack. We characterize the attacker's optimal attack strategy, and further introduce adversarial influence function (AIF) to quantify an estimator's sensiti…
