Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al. (2019) showed that this vulnerability arises, in part, because neural network classifiers rely on highly predictive but brittle "non-robust" features. In this paper we extend the work of Ilyas et al. by investigating the nature of the input patterns that give rise to these features. In particular, we hypothesize that in a neural network trained in a standard way, non-robust features respond to small, "non-semantic" patterns that are typically entangled with larger, robust patterns, known to be more human-interpretable, as opposed to solely responding to statistical artifacts in a dataset. Thus, adversarial examples can be formed via minimal perturbations to these small, entangled patterns. In addition, we demonstrate a corollary of our hypothesis: robust classifiers are more effective than standard (non-robust) ones as a source for generating transferable adversarial examples in both the untargeted and targeted settings. The results we present in this paper provide new insight into the nature of the non-robust features responsible for adversarial vulnerability of neural network classifiers.
University of British Columbia（不列颠哥伦比亚大学）；Lawrence Livermore National Laboratory（劳伦斯利弗莫尔国家实验室）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）
Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS algorithms extract pixel-level pseudo-labels from an image classifier - a very difficult task to do well, hence requiring complicated architectures and extensive hyperparameter tuning on fully-supervised validation sets. We propose a method called prediction filtering, which instead of extracting pseudo-labels, just uses the classifier as a classifier: it ignores…
Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broaden the use of ML models, cloud-based services offered by Microsoft, Amazon, Google, and others have developed ML-as-a-service tools as black-box systems. However, ML classifiers are vulnerable to adversarial examples: inputs that are maliciously modified can cause the classifier to provide adversary-desired outputs. Moreover, it is known that adversarial examples generated on one classifier are likely to cause anoth…
University of Florida（佛罗里达大学）；National Cheng Kung University（国立成功大学）；University of Central Florida（中佛罗里达大学）
Machine learning researchers have long noticed the phenomenon that the model training process will be more effective and efficient when the training samples are densely sampled around the underlying decision boundary. While this observation has already been widely applied in a range of machine learning security techniques, it lacks theoretical analyses of the correctness of the observation. To address this challenge, we first add particular perturbation to original training examples using adversarial attack methods so that the generated examples could lie approximately on the decision boundary…
Facebook AI Research（Facebook人工智能研究院）；LAMSADE, Université Paris-Dauphine（巴黎多芬大学LAMSADE实验室）；Institut LIST, CEA, Université Paris-Saclay（巴黎萨克雷大学CEA LIST研究所）；Ecole Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
This paper investigates the theory of robustness against adversarial attacks. We focus on randomized classifiers (\emph{i.e.} classifiers that output random variables) and provide a thorough analysis of their behavior through the lens of statistical learning theory and information theory. To this aim, we introduce a new notion of robustness for randomized classifiers, enforcing local Lipschitzness using probability metrics. Equipped with this definition, we make two new contributions. The first one consists in devising a new upper bound on the adversarial generalization gap of randomized class…
Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles
Centre for Computational and Data Sciences, IIT Kharagpur（印度理工学院克勒格布尔分校计算与数据科学中心）；Computer Science and Engineering Department, IIT Kharagpur（印度理工学院克勒格布尔分校计算机科学与工程系）；Center for Cyber Security, New York University Abu Dhabi（纽约大学阿布扎比分校网络安全中心）；Department of Artificial Intelligence, IIT Kharagpur（印度理工学院克勒格布尔分校人工智能系）；Computer Science and Engineering Department, IIT Patna（印度理工学院巴特那分校计算机科学与工程系）
Air Force Research Lab（空军研究实验室）；Miami University（迈阿密大学）；General Mills（通用磨坊公司）
Given a black-box classification model and an unlabeled evaluation dataset from some application domain, efficient strategies need to be developed to evaluate the model. Random sampling allows a user to estimate metrics like accuracy, precision, and recall, but may not provide insight to high-confidence errors. High-confidence errors are rare events for which the model is highly confident in its prediction, but is wrong. Such errors can represent costly mistakes and should be explicitly searched for. In this paper we propose a generalization to the Adversarial Distance search that leverages co…
Technion – Israel Institute of Technology（技术学院 – 以色列理工学院）；Bar-Ilan University（巴伊兰大学）；Ben-Gurion University of the Negev（贝加尔大学）；Institute of Science and Technology（科学与技术研究所）
Neural network classifiers are vulnerable to misclassification of adversarial samples, for which the current best defense trains classifiers with adversarial samples. However, adversarial samples are not optimal for steering attack convergence, based on the minimization at the core of adversarial attacks. The minimization perturbation term can be minimized towards $0$ by replacing adversarial samples in training with duplicated original samples, labeled differently only for training. Using only original samples, Target Training eliminates the need to generate adversarial samples for training a…
Deep neural network (DNN) models are wellknown to easily misclassify prediction results by using input images with small perturbations, called adversarial examples. In this paper, we propose a novel adversarial detector, which consists of a robust classifier and a plain one, to highly detect adversarial examples. The proposed adversarial detector is carried out in accordance with the logits of plain and robust classifiers. In an experiment, the proposed detector is demonstrated to outperform a state-of-the-art detector without any robust classifier.
Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities. Despite significant recent work on adversarial example generation targeting image classifiers, relatively little work exists exploring adversarial example generation for text classifiers; additionally, many existing adversarial example generation algorithms require full access to target model parameters, rendering them impractical for many real-world attacks. In…
In malware behavioral analysis, the list of accessed and created files very often indicates whether the examined file is malicious or benign. However, malware authors are trying to avoid detection by generating random filenames and/or modifying used filenames with new versions of the malware. These changes represent real-world adversarial examples. The goal of this work is to generate realistic adversarial examples and improve the classifier's robustness against these attacks. Our approach learns latent representations of input strings in an unsupervised fashion and uses gradient-based adversa…
Recently, some works found an interesting phenomenon that adversarially robust classifiers can generate good images comparable to generative models. We investigate this phenomenon from an energy perspective and provide a novel explanation. We reformulate adversarial example generation, adversarial training, and image generation in terms of an energy function. We find that adversarial training contributes to obtaining an energy function that is flat and has low energy around the real data, which is the key for generative capability. Based on our new understanding, we further propose a better ad…
We consider the problem of prediction by a machine learning algorithm, called learner, within an adversarial learning setting. The learner's task is to correctly predict the class of data passed to it as a query. However, along with queries containing clean data, the learner could also receive malicious or adversarial queries from an adversary. The objective of the adversary is to evade the learner's prediction mechanism by sending adversarial queries that result in erroneous class prediction by the learner, while the learner's objective is to reduce the incorrect prediction of these adversari…
State-of-the-art machine learning models frequently misclassify inputs that have been perturbed in an adversarial manner. Adversarial perturbations generated for a given input and a specific classifier often seem to be effective on other inputs and even different classifiers. In other words, adversarial perturbations seem to transfer between different inputs, models, and even different neural network architectures. In this work, we show that in the context of linear classifiers and two-layer ReLU networks, there provably exist directions that give rise to adversarial perturbations for many cla…
Being an emerging class of in-memory computing architecture, brain-inspired hyperdimensional computing (HDC) mimics brain cognition and leverages random hypervectors (i.e., vectors with a dimensionality of thousands or even more) to represent features and to perform classification tasks. The unique hypervector representation enables HDC classifiers to exhibit high energy efficiency, low inference latency and strong robustness against hardware-induced bit errors. Consequently, they have been increasingly recognized as an appealing alternative to or even replacement of traditional deep neural ne…
We provide a methodology, resilient feature engineering, for creating adversarially resilient classifiers. According to existing work, adversarial attacks identify weakly correlated or non-predictive features learned by the classifier during training and design the adversarial noise to utilize these features. Therefore, highly predictive features should be used first during classification in order to determine the set of possible output labels. Our methodology focuses the problem of designing resilient classifiers into a problem of designing resilient feature extractors for these highly predic…
Microsoft Research Cambridge（微软研究院剑桥分院）；University of Cambridge（剑桥大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Eberhard Karls University of Tübingen（图宾根大学）
There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. However, most recent work focuses on discriminative classifiers, which only model the conditional distribution of the labels given the inputs. In this paper, we propose and investigate the deep Bayes classifier, which improves classical naive Bayes with conditional deep generative models. We further develop detection methods for adversarial examples, which reject inputs with low likelihood under the generative m…
Uni. of Glasgow/Turing Institute（格拉斯哥大学/图灵研究所）；UCL/Turing Institute（伦敦大学学院/图灵研究所）；Amazon Tübingen（亚马逊图宾根）
We present a simple regularization of adversarial perturbations based upon the perceptual loss. While the resulting perturbations remain imperceptible to the human eye, they differ from existing adversarial perturbations in that they are semi-sparse alterations that highlight objects and regions of interest while leaving the background unaltered. As a semantically meaningful adverse perturbations, it forms a bridge between counterfactual explanations and adversarial perturbations in the space of images. We evaluate our approach on several standard explainability benchmarks, namely, weak locali…
Deep neural networks have been shown to exhibit an intriguing vulnerability to adversarial input images corrupted with imperceptible perturbations. However, the majority of adversarial attacks assume global, fine-grained control over the image pixel space. In this paper, we consider a different setting: what happens if the adversary could only alter specific attributes of the input image? These would generate inputs that might be perceptibly different, but still natural-looking and enough to fool a classifier. We propose a novel approach to generate such `semantic' adversarial examples by opti…
On the Generalization of Adversarially Trained Quantum Classifiers
Department of Computer Science, University of Birmingham, UK（英国伯明翰大学计算机科学系）；KCLIP Lab Centre for Intelligent Information Processing Systems (CIIPS) Department of Engineering, King’s College London, UK（伦敦国王学院工程系智能信息处理系统中心）
Adversarial approach has been widely used for data generation in the last few years. However, this approach has not been extensively utilized for classifier training. In this paper, we propose an adversarial framework for classifier training that can also handle imbalanced data. Indeed, a network is trained via an adversarial approach to give weights to samples of the majority class such that the obtained classification problem becomes more challenging for the discriminator and thus boosts its classification capability. In addition to the general imbalanced classification problems, the propose…
An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images and other structured model inputs, but not for categorical sequences models. Successful attacks on classifiers of categorical sequences are challenging because the model input is tokens from finite sets, so a classifier score is non-differentiable with respect to inputs, and gradient-based attacks are not applicable. Common approaches deal with this problem w…
Recently, it has been shown that, in spite of the significant performance of deep neural networks in different fields, those are vulnerable to adversarial examples. In this paper, we propose a gradient-based adversarial attack against transformer-based text classifiers. The adversarial perturbation in our method is imposed to be block-sparse so that the resultant adversarial example differs from the original sentence in only a few words. Due to the discrete nature of textual data, we perform gradient projection to find the minimizer of our proposed optimization problem. Experimental results de…
In this work, we investigate the phenomenon that robust image classifiers have human-recognizable features -- often referred to as interpretability -- as revealed through the input gradients of their score functions and their subsequent adversarial perturbations. In particular, we demonstrate that state-of-the-art methods for adversarial training incorporate two terms -- one that orients the decision boundary via minimizing the expected loss, and another that induces smoothness of the classifier's decision surface by penalizing the local Lipschitz constant. Through this demonstration, we provi…
Adversarial robustness has become an important research topic given empirical demonstrations on the lack of robustness of deep neural networks. Unfortunately, recent theoretical results suggest that adversarial training induces a strict tradeoff between classification accuracy and adversarial robustness. In this paper, we propose and then study a new regularization for any margin classifier or deep neural network. We motivate this regularization by a novel generalization bound that shows a tradeoff in classifier accuracy between maximizing its margin and average margin. We thus call our approa…
This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples. While recent machine learning algorithms achieve high prediction performance, they are empirically vulnerable to adversarial examples, which are slightly perturbed data samples that are wrongly classified. In real-world applications, adversarial attacks using such adversarial examples could cause serious problems. To this end, various methods are proposed to obtain a classifier that is robust against adversarial examples. Adversarial training is one o…
Adversarial attack has cast a shadow on the massive success of deep neural networks. Despite being almost visually identical to the clean data, the adversarial images can fool deep neural networks into wrong predictions with very high confidence. In this paper, however, we show that we can build a simple binary classifier separating the adversarial apart from the clean data with accuracy over 99%. We also empirically show that the binary classifier is robust to a second-round adversarial attack. In other words, it is difficult to disguise adversarial samples to bypass the binary classifier. Fu…
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ adversarial training to improve the performance of randomized smoothing. We design an adapted attack for smoothed classifiers, and we show how this attack can be used in an adversarial training setting to boost the provable robustness of smoothed classifiers. We demonstrate through extensive experimentation that our method consistently outperforms all existing provabl…
Machine learning based solutions have been very helpful in solving problems that deal with immense amounts of data, such as malware detection and classification. However, deep neural networks have been found to be vulnerable to adversarial examples, or inputs that have been purposefully perturbed to result in an incorrect label. Researchers have shown that this vulnerability can be exploited to create evasive malware samples. However, many proposed attacks do not generate an executable and instead generate a feature vector. To fully understand the impact of adversarial examples on malware dete…
Huazhong University of Science and Technology（华中科技大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Duke University（杜克大学）
Encoder as a service is an emerging cloud service. Specifically, a service provider first pre-trains an encoder (i.e., a general-purpose feature extractor) via either supervised learning or self-supervised learning and then deploys it as a cloud service API. A client queries the cloud service API to obtain feature vectors for its training/testing inputs when training/testing its classifier (called downstream classifier). A downstream classifier is vulnerable to adversarial examples, which are testing inputs with carefully crafted perturbation that the downstream classifier misclassifies. There…
In this paper, we propose Code-Bridged Classifier (CBC), a framework for making a Convolutional Neural Network (CNNs) robust against adversarial attacks without increasing or even by decreasing the overall models' computational complexity. More specifically, we propose a stacked encoder-convolutional model, in which the input image is first encoded by the encoder module of a denoising auto-encoder, and then the resulting latent representation (without being decoded) is fed to a reduced complexity CNN for image classification. We illustrate that this network not only is more robust to adversari…
Adversarial robustness of machine learning models has attracted considerable attention over recent years. Adversarial attacks undermine the reliability of and trust in machine learning models, but the construction of more robust models hinges on a rigorous understanding of adversarial robustness as a property of a given model. Point-wise measures for specific threat models are currently the most popular tool for comparing the robustness of classifiers and are used in most recent publications on adversarial robustness. In this work, we use recently proposed robustness curves to show that point-…
Faculty of Information Technology, Brno University of Technology（布尔诺理工大学信息技术学院）
In this paper, we present three datasets that have been built from network traffic traces using ASNM features, designed in our previous work. The first dataset was built using a state-of-the-art dataset called CDX 2009, while the remaining two datasets were collected by us in 2015 and 2018, respectively. These two datasets contain several adversarial obfuscation techniques that were applied onto malicious as well as legitimate traffic samples during the execution of particular TCP network connections. Adversarial obfuscation techniques were used for evading machine learning-based network intru…
Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the underlying models. Cost-sensitive predictions are then achieved via a final processing step in the feed-forward evaluation of the network. We evaluate the effectiveness of cost-sensitive classifiers against a variety of attacks and we introduce a new cost-sensitive attack which performs better than targeted attacks in some cases. We also explored the measures a defender can take…
University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）
With the recent developments in artificial intelligence and machine learning, anomalies in network traffic can be detected using machine learning approaches. Before the rise of machine learning, network anomalies which could imply an attack, were detected using well-crafted rules. An attacker who has knowledge in the field of cyber-defence could make educated guesses to sometimes accurately predict which particular features of network traffic data the cyber-defence mechanism is looking at. With this information, the attacker can circumvent a rule-based cyber-defense system. However, after the …
Machine-learning techniques are widely used in security-related applications, like spam and malware detection. However, in such settings, they have been shown to be vulnerable to adversarial attacks, including the deliberate manipulation of data at test time to evade detection. In this work, we focus on the vulnerability of linear classifiers to evasion attacks. This can be considered a relevant problem, as linear classifiers have been increasingly used in embedded systems and mobile devices for their low processing time and memory requirements. We exploit recent findings in robust optimizatio…
We consider the problem of finding optimal classifiers in an adversarial setting where the class-1 data is generated by an attacker whose objective is not known to the defender -- an aspect that is key to realistic applications but has so far been overlooked in the literature. To model this situation, we propose a Bayesian game framework where the defender chooses a classifier with no a priori restriction on the set of possible classifiers. The key difficulty in the proposed framework is that the set of possible classifiers is exponential in the set of possible data, which is itself exponentia…
Machine learning models are vulnerable to adversarial perturbations, that when added to an input, can cause high confidence misclassifications. The adversarial learning research community has made remarkable progress in the understanding of the root causes of adversarial perturbations. However, most problems that one may consider important to solve for the deployment of machine learning in safety critical tasks involve high dimensional complex manifolds that are difficult to characterize and study. It is common to develop adversarially robust learning theory on simple problems, in the hope tha…
University of California, Santa Barbara（加州大学圣巴巴拉分校）；UC, Davis Health（加州大学戴维斯分校医疗中心）
Multiple organ failure (MOF) is a severe syndrome with a high mortality rate among Intensive Care Unit (ICU) patients. Early and precise detection is critical for clinicians to make timely decisions. An essential challenge in applying machine learning models to electronic health records (EHRs) is the pervasiveness of missing values. Most existing imputation methods are involved in the data preprocessing phase, failing to capture the relationship between data and outcome for downstream predictions. In this paper, we propose classifier-guided generative adversarial imputation networks Classifier…
Management Center Innsbruck（因斯布鲁克管理中心）；Department of Computers and Engineering, Czech Technical University in Prague（布拉格捷克理工大学计算机与工程系）
Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic scenarios where costs for adversary and defender are not considered and either all samples or no samples are adversarially perturbed. We scrutinize these assumptions and propose the advanced adversarial classification game, which incorporates all relevant parameters of an adversary and a defender. Especially, we take into account economic factors on both sides an…
We address the problem of abnormal event detection from trajectory data. In this paper, a new adversarial approach is proposed for building a deep neural network binary classifier, trained in an unsupervised fashion, that can distinguish normal from abnormal trajectory-based events without the need for setting manual detection threshold. Inspired by the generative adversarial network (GAN) framework, our GAN version is a discriminative one in which the discriminator is trained to distinguish normal and abnormal trajectory reconstruction errors given by a deep autoencoder. With urban traffic vi…
We explore adversarial robustness in the setting in which it is acceptable for a classifier to abstain---that is, output no class---on adversarial examples. Adversarial examples are small perturbations of normal inputs to a classifier that cause the classifier to give incorrect output; they present security and safety challenges for machine learning systems. In many safety-critical applications, it is less costly for a classifier to abstain on adversarial examples than to give incorrect output for them. We first introduce a novel objective function for adversarial robustness with an abstain op…
Ecole Polytechnique Federale de Lausanne (EPFL)（洛桑联邦理工学院）；ENS de Lyon（里昂高等师范学院）；Université de Lyon（里昂大学）
The goal of this paper is to analyze an intriguing phenomenon recently discovered in deep networks, namely their instability to adversarial perturbations (Szegedy et. al., 2014). We provide a theoretical framework for analyzing the robustness of classifiers to adversarial perturbations, and show fundamental upper bounds on the robustness of classifiers. Specifically, we establish a general upper bound on the robustness of classifiers to adversarial perturbations, and then illustrate the obtained upper bound on the families of linear and quadratic classifiers. In both cases, our upper bound dep…
Despite the enormous success of machine learning models in various applications, most of these models lack resilience to (even small) perturbations in their input data. Hence, new methods to robustify machine learning models seem very essential. To this end, in this paper we consider the problem of binary classification with adversarial perturbations. Investigating the solution to a min-max optimization (which considers the worst-case loss in the presence of adversarial perturbations) we introduce a generalization to the max-margin classifier which takes into account the power of the adversary…
As the name suggests, image spam is spam email that has been embedded in an image. Image spam was developed in an effort to evade text-based filters. Modern deep learning-based classifiers perform well in detecting typical image spam that is seen in the wild. In this chapter, we evaluate numerous adversarial techniques for the purpose of attacking deep learning-based image spam classifiers. Of the techniques tested, we find that universal perturbation performs best. Using universal adversarial perturbations, we propose and analyze a new transformation-based adversarial attack that enables us t…
New Jersey Institute of Technology（新泽西理工学院）；Qatar Computing Research Institute（卡塔尔计算研究所）
In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a carefully crafted adversarial perturbation is injected into the input examples during inference, and 2) a Trojan backdoor is implanted during the training process of the model. We leverage adversarial noise in the input space to move Trojan-infected examples across the model decision boundary, making it difficult to detect. The stealthiness behavior of AdvTrojan …
Generating Universal Adversarial Perturbations for Quantum Classifiers
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；University of British Columbia（不列颠哥伦比亚大学）；University of Western Ontario（西安大略大学）；University of Waterloo（滑铁卢大学）
National University of Ireland Galway（爱尔兰国立大学戈尔韦分校）
One of the most interesting challenges in Artificial Intelligence is to train conditional generators which are able to provide labeled adversarial samples drawn from a specific distribution. In this work, a new framework is presented to train a deep conditional generator by placing a classifier in parallel with the discriminator and back propagate the classification error through the generator network. The method is versatile and is applicable to any variations of Generative Adversarial Network (GAN) implementation, and also gives superior results compared to similar methods.
