Neural networks are susceptible to artificially designed adversarial perturbations. Recent efforts have shown that imposing certain modifications on classification layer can improve the robustness of the neural networks. In this paper, we explicitly construct a dense orthogonal weight matrix whose entries have the same magnitude, thereby leading to a novel robust classifier. The proposed classifier avoids the undesired structural redundancy issue in previous work. Applying this classifier in standard training on clean data is sufficient to ensure the high accuracy and good robustness of the model. Moreover, when extra adversarial samples are used, better robustness can be further obtained with the help of a special worst-case loss. Experimental results show that our method is efficient and competitive to many state-of-the-art defensive approaches. Our code is available at \url{https://github.com/MTandHJ/roboc}.
College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）；Stony Brook University（石溪大学）
Light-based adversarial attacks use spatial augmented reality (SAR) techniques to fool image classifiers by altering the physical light condition with a controllable light source, e.g., a projector. Compared with physical attacks that place hand-crafted adversarial objects, projector-based ones obviate modifying the physical entities, and can be performed transiently and dynamically by altering the projection pattern. However, subtle light perturbations are insufficient to fool image classifiers, due to the complex environment and project-and-capture process. Thus, existing approaches focus on…
University of California, Davis（加利福尼亚大学戴维斯分校）；NEC Laboratories America（NEC美国实验室）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Recent studies have demonstrated the vulnerability of deep convolutional neural networks against adversarial examples. Inspired by the observation that the intrinsic dimension of image data is much smaller than its pixel space dimension and the vulnerability of neural networks grows with the input dimension, we propose to embed high-dimensional input images into a low-dimensional space to perform classification. However, arbitrarily projecting the input images to a low-dimensional space without regularization will not improve the robustness of deep neural networks. Leveraging optimal transport…
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…
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…
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…
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…
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…
Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations. In this paper, we propose another type of adversarial attack that can cheat classifiers by significant changes. For example, we can significantly change a face but well-trained neural networks still recognize the adversarial and the original example as the same person. Statistically, the existing adversarial attack increases Type II error and the proposed one aims at Type I error, which are hence named as Type II and Type I adversarial attack, respectively. T…
Classifiers fail to classify correctly input images that have been purposefully and imperceptibly perturbed to cause misclassification. This susceptability has been shown to be consistent across classifiers, regardless of their type, architecture or parameters. Common defenses against adversarial attacks modify the classifer boundary by training on additional adversarial examples created in various ways. In this paper, we introduce AutoGAN, which counters adversarial attacks by enhancing the lower-dimensional manifold defined by the training data and by projecting perturbed data points onto it…
Deep Neural Networks (DNNs) are often criticized for being susceptible to adversarial attacks. Most successful defense strategies adopt adversarial training or random input transformations that typically require retraining or fine-tuning the model to achieve reasonable performance. In this work, our investigations of intermediate representations of a pre-trained DNN lead to an interesting discovery pointing to intrinsic robustness to adversarial attacks. We find that we can learn a generative classifier by statistically characterizing the neural response of an intermediate layer to clean train…
School of Computer Science and Engineering（计算机科学与工程学院）；The Hebrew University of Jerusalem（耶路撒冷希伯来大学）
Since the discovery of adversarial examples - the ability to fool modern CNN classifiers with tiny perturbations of the input, there has been much discussion whether they are a "bug" that is specific to current neural architectures and training methods or an inevitable "feature" of high dimensional geometry. In this paper, we argue for examining adversarial examples from the perspective of Bayes-Optimal classification. We construct realistic image datasets for which the Bayes-Optimal classifier can be efficiently computed and derive analytic conditions on the distributions under which these cl…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；University of California, Davis（加利福尼亚大学戴维斯分校）
Few-shot image classification, where the goal is to generalize to tasks with limited labeled data, has seen great progress over the years. However, the classifiers are vulnerable to adversarial examples, posing a question regarding their generalization capabilities. Recent works have tried to combine meta-learning approaches with adversarial training to improve the robustness of few-shot classifiers. We show that a simple transfer-learning based approach can be used to train adversarially robust few-shot classifiers. We also present a method for novel classification task based on calibrating t…
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified activations to reconstruct the original sample. A human might (and possibly should) notice differences between the original and the adversarial sample. Depending on the attacker-provided constraints, an adversarial sample can exhibit subtle differences or appear like a "forged" sample from another class. Our approach and goal are in stark contrast to common att…
University of Maryland, College Park（马里兰大学帕克分校）；University of Maryland Institute for Advanced Computer Studies（马里兰大学高级计算机研究所）
In recent years, deep neural network approaches have been widely adopted for machine learning tasks, including classification. However, they were shown to be vulnerable to adversarial perturbations: carefully crafted small perturbations can cause misclassification of legitimate images. We propose Defense-GAN, a new framework leveraging the expressive capability of generative models to defend deep neural networks against such attacks. Defense-GAN is trained to model the distribution of unperturbed images. At inference time, it finds a close output to a given image which does not contain the adv…
Deep-learning based classification algorithms have been shown to be susceptible to adversarial attacks: minor changes to the input of classifiers can dramatically change their outputs, while being imperceptible to humans. In this paper, we present a simple hypothesis about a feature compression property of artificial intelligence (AI) classifiers and present theoretical arguments to show that this hypothesis successfully accounts for the observed fragility of AI classifiers to small adversarial perturbations. Drawing on ideas from information and coding theory, we propose a general class of de…
School of Computing and Information Systems（计算与信息系统学院）；The University of Melbourne（墨尔本大学）
Deep learning classifiers are susceptible to well-crafted, imperceptible variations of their inputs, known as adversarial attacks. In this regard, the study of powerful attack models sheds light on the sources of vulnerability in these classifiers, hopefully leading to more robust ones. In this paper, we introduce AdvFlow: a novel black-box adversarial attack method on image classifiers that exploits the power of normalizing flows to model the density of adversarial examples around a given target image. We see that the proposed method generates adversaries that closely follow the clean data di…
Point cloud classifiers with rotation robustness have been widely discussed in the 3D deep learning community. Most proposed methods either use rotation invariant descriptors as inputs or try to design rotation equivariant networks. However, robust models generated by these methods have limited performance under clean aligned datasets due to modifications on the original classifiers or input space. In this study, for the first time, we show that the rotation robustness of point cloud classifiers can also be acquired via adversarial training with better performance on both rotated and clean dat…
University of Kansas（堪萨斯大学）；Worcester Polytechnic Institute（伍斯特理工学院）；Ryerson University（瑞尔森大学）
Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn to denoise the (attacked) point clouds by reconstruction, and then feed them to the classifiers as input. In contrast to the literature, we propose a family of robust structured declarative classifiers for point cloud classification, where the internal constrained optimization mechanism can effectively defend adversarial attacks through implicit gradients. Such classifiers can be formulated using a bilevel optimizati…
Prior state-of-the-art adversarial detection works are classifier model dependent, i.e., they require classifier model outputs and parameters for training the detector or during adversarial detection. This makes their detection approach classifier model specific. Furthermore, classifier model outputs and parameters might not always be accessible. To this end, we propose a classifier model independent adversarial detection method using a simple energy function to distinguish between adversarial and natural inputs. We train a standalone detector independent of the classifier model, with a layer-…
Privacy concerns in the modern digital age have prompted researchers to develop techniques that allow users to selectively suppress certain information in collected data while allowing for other information to be extracted. In this regard, Semi-Adversarial Networks (SAN) have recently emerged as a method for imparting soft-biometric privacy to face images. SAN enables modifications of input face images so that the resulting face images can still be reliably used by arbitrary conventional face matchers for recognition purposes, while attribute classifiers, such as gender classifiers, are confou…
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.
Computer Science and Artificial Intelligence Lab（计算机科学与人工智能实验室）；Massachusetts Institute of Technology（麻省理工学院）
We propose to identify directions invariant to a given classifier so that these directions can be controlled in tasks such as style transfer. While orthogonal decomposition is directly identifiable when the given classifier is linear, we formally define a notion of orthogonality in the non-linear case. We also provide a surprisingly simple method for constructing the orthogonal classifier (a classifier utilizing directions other than those of the given classifier). Empirically, we present three use cases where controlling orthogonal variation is important: style transfer, domain adaptation, an…
Indiana University-Purdue University Indianapolis（印第安纳大学-普渡大学印第安纳波利斯分校）
Unsupervised Domain adaptation (UDA) attempts to recognize the unlabeled target samples by building a learning model from a differently-distributed labeled source domain. Conventional UDA concentrates on extracting domain-invariant features through deep adversarial networks. However, most of them seek to match the different domain feature distributions, without considering the task-specific decision boundaries across various classes. In this paper, we propose a novel Adversarial Dual Distinct Classifiers Network (AD$^2$CN) to align the source and target domain data distribution simultaneously …
Deep learning has greatly improved visual recognition in recent years. However, recent research has shown that there exist many adversarial examples that can negatively impact the performance of such an architecture. This paper focuses on detecting those adversarial examples by analyzing whether they come from the same distribution as the normal examples. Instead of directly training a deep neural network to detect adversarials, a much simpler approach was proposed based on statistics on outputs from convolutional layers. A cascade classifier was designed to efficiently detect adversarials. Fu…
Recent research has proposed the use of Semi Adversarial Networks (SAN) for imparting privacy to face images. SANs are convolutional autoencoders that perturb face images such that the perturbed images cannot be reliably used by an attribute classifier (e.g., a gender classifier) but can still be used by a face matcher for matching purposes. However, the generalizability of SANs across multiple arbitrary gender classifiers has not been demonstrated in the literature. In this work, we tackle the generalization issue by designing an ensemble SAN model that generates a diverse set of perturbed ou…
Nowadays a steganography has to face challenges of both feature based staganalysis and convolutional neural network (CNN) based steganalysis. In this paper, we present a novel steganography scheme denoted as ITE-SYN (based on ITEratively adversarial perturbations onto a SYNchronized-directions sub-image), by which security data is embedded with synchronizing modification directions to enhance security and then iteratively increased perturbations are added onto a sub-image to reduce loss with cover class label of the target CNN classifier. Firstly an exist steganographic function is employed to…
The success of deep learning research has catapulted deep models into production systems that our society is becoming increasingly dependent on, especially in the image and video domains. However, recent work has shown that these largely uninterpretable models exhibit glaring security vulnerabilities in the presence of an adversary. In this work, we develop a powerful untargeted adversarial attack for action recognition systems in both white-box and black-box settings. Action recognition models differ from image-classification models in that their inputs contain a temporal dimension, which we …
Baidu Inc.（百度公司）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；University of Science and Technology of China（中国科学技术大学）；Hunan University（湖南大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Unsupervised Domain Adaptation (UDA), which aims to explore the transferrable features from a well-labeled source domain to a related unlabeled target domain, has been widely progressed. Nevertheless, as one of the mainstream, existing adversarial-based methods neglect to filter the irrelevant semantic knowledge, hindering adaptation performance improvement. Besides, they require an additional domain discriminator that strives extractor to generate confused representations, but discrete designing may cause model collapse. To tackle the above issues, we propose Crucial Semantic Classifier-based…
We present a method to create universal, robust, targeted adversarial image patches in the real world. The patches are universal because they can be used to attack any scene, robust because they work under a wide variety of transformations, and targeted because they can cause a classifier to output any target class. These adversarial patches can be printed, added to any scene, photographed, and presented to image classifiers; even when the patches are small, they cause the classifiers to ignore the other items in the scene and report a chosen target class. To reproduce the results from the pap…
University of Science and Technology of China（中国科学技术大学）
Adversarial learning has achieved remarkable performances for unsupervised domain adaptation (UDA). Existing adversarial UDA methods typically adopt an additional discriminator to play the min-max game with a feature extractor. However, most of these methods failed to effectively leverage the predicted discriminative information, and thus cause mode collapse for generator. In this work, we address this problem from a different perspective and design a simple yet effective adversarial paradigm in the form of a discriminator-free adversarial learning network (DALN), wherein the category classifi…
NortonLifeLock Research Group（NortonLifeLock研究集团）；Carnegie Mellon University（卡内基梅隆大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
This paper proposes a new defense called $n$-ML against adversarial examples, i.e., inputs crafted by perturbing benign inputs by small amounts to induce misclassifications by classifiers. Inspired by $n$-version programming, $n$-ML trains an ensemble of $n$ classifiers, and inputs are classified by a vote of the classifiers in the ensemble. Unlike prior such approaches, however, the classifiers in the ensemble are trained specifically to classify adversarial examples differently, rendering it very difficult for an adversarial example to obtain enough votes to be misclassified. We show that $n…
The vulnerability of convolutional neural networks (CNNs) to image perturbations such as common corruptions and adversarial perturbations has recently been investigated from the perspective of frequency. In this study, we investigate the effect of the amplitude and phase spectra of adversarial images on the robustness of CNN classifiers. Extensive experiments revealed that the images generated by combining the amplitude spectrum of adversarial images and the phase spectrum of clean images accommodates moderate and general perturbations, and training with these images equips a CNN classifier wi…
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…
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…
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…
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.
New Jersey Institute of Technology（新泽西理工学院）；Qatar Computing Research Institute（卡塔尔计算研究所）
Machine learning models, especially neural network (NN) classifiers, are widely used in many applications including natural language processing, computer vision and cybersecurity. They provide high accuracy under the assumption of attack-free scenarios. However, this assumption has been defied by the introduction of adversarial examples -- carefully perturbed samples of input that are usually misclassified. Many researchers have tried to develop a defense against adversarial examples; however, we are still far from achieving that goal. In this paper, we design a Generative Adversarial Net (GAN…
Most machine learning classifiers, including deep neural networks, are vulnerable to adversarial examples. Such inputs are typically generated by adding small but purposeful modifications that lead to incorrect outputs while imperceptible to human eyes. The goal of this paper is not to introduce a single method, but to make theoretical steps towards fully understanding adversarial examples. By using concepts from topology, our theoretical analysis brings forth the key reasons why an adversarial example can fool a classifier ($f_1$) and adds its oracle ($f_2$, like human eyes) in such analysis.…
Generative Adversarial Networks (GAN) receive great attentions recently due to its excellent performance in image generation, transformation, and super-resolution. However, GAN has rarely been studied and trained for classification, leading that the generated images may not be appropriate for classification. In this paper, we propose a novel Generative Adversarial Classifier (GAC) particularly for low-resolution Handwriting Character Recognition. Specifically, involving additionally a classifier in the training process of normal GANs, GAC is calibrated for learning suitable structures and rest…
Univ Lyon（里昂大学）；ENS de Lyon（里昂高等师范学院）；CNRS（法国国家科学研究中心）；UCBL（里昂第一大学）；DeepMind（深度思维）；University of Cambridge（剑桥大学）
Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we study the phenomenon of adversarial perturbations under the assumption that the data is generated with a smooth generative model. We derive fundamental upper bounds on the robustness to perturbations of any classification function, and prove the existence of adversarial perturbations that transfer well across different classifiers with small risk. Our analy…
Due to the sparsity of features, noise has proven to be a great inhibitor in the classification of handwritten characters. To combat this, most techniques perform denoising of the data before classification. In this paper, we consolidate the approach by training an all-in-one model that is able to classify even noisy characters. For classification, we progressively train a classifier generative adversarial network on the characters from low to high resolution. We show that by learning the features at each resolution independently a trained model is able to accurately classify characters even i…
School of Electrical and Electronic Engineering（电气与电子工程学院）；Nanyang Technological University（南洋理工大学）
Ideally, what confuses neural network should be confusing to humans. However, recent experiments have shown that small, imperceptible perturbations can change the network prediction. To address this gap in perception, we propose a novel approach for learning robust classifier. Our main idea is: adversarial examples for the robust classifier should be indistinguishable from the regular data of the adversarial target. We formulate a problem of learning robust classifier in the framework of Generative Adversarial Networks (GAN), where the adversarial attack on classifier acts as a generator, and …
Department of Mathematics and Computer Science（数学与计算机科学系）；Saarland University（萨尔大学）
Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small adversarial change of an originally with high confidence correctly classified input leads to a wrong classification again with high confidence. This raises concerns that such classifiers are vulnerable to attacks and calls into question their usage in safety-critical systems. We show in this paper for the first time formal guarantees on the robustness of a classifier by giving instance-specific lower bounds on the norm of the input manipulation required to change the classifier decision. Based …
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Several recent works have shown that state-of-the-art classifiers are vulnerable to worst-case (i.e., adversarial) perturbations of the datapoints. On the other hand, it has been empirically observed that these same classifiers are relatively robust to random noise. In this paper, we propose to study a \textit{semi-random} noise regime that generalizes both the random and worst-case noise regimes. We propose the first quantitative analysis of the robustness of nonlinear classifiers in this general noise regime. We establish precise theoretical bounds on the robustness of classifiers in this ge…
Deep learning is a popular and powerful tool in computed tomography (CT) image processing such as organ segmentation, but its requirement of large training datasets remains a challenge. Even though there is a large anatomical variability for children during their growth, the training datasets for pediatric CT scans are especially hard to obtain due to risks of radiation to children. In this paper, we propose a method to conditionally synthesize realistic pediatric CT images using a new auxiliary classifier generative adversarial network (ACGAN) architecture by taking age information into accou…
Multiple different approaches of generating adversarial examples have been proposed to attack deep neural networks. These approaches involve either directly computing gradients with respect to the image pixels, or directly solving an optimization on the image pixels. In this work, we present a fundamentally new method for generating adversarial examples that is fast to execute and provides exceptional diversity of output. We efficiently train feed-forward neural networks in a self-supervised manner to generate adversarial examples against a target network or set of networks. We call such a net…
The attacks on the neural-network-based classifiers using adversarial images have gained a lot of attention recently. An adversary can purposely generate an image that is indistinguishable from a innocent image for a human being but is incorrectly classified by the neural networks. The adversarial images do not need to be tuned to a particular architecture of the classifier - an image that fools one network can fool another one with a certain success rate.The published works mostly concentrate on the use of modified image files for attacks against the classifiers trained on the model databases…
AZAD Research Lab（AZAD研究实验室）；Sweden（瑞典（注：此处Sweden为国家，非机构，根据要求应忽略。但原HTML中“Affiliation: Sweden”可能是笔误或格式错误，若仅保留明确的机构名“AZAD Research Lab”）。修正后应为：{）
Facial expressions are a form of non-verbal communication that humans perform seamlessly for meaningful transfer of information. Most of the literature addresses the facial expression recognition aspect however, with the advent of Generative Models, it has become possible to explore the affect space in addition to mere classification of a set of expressions. In this article, we propose a generative model architecture which robustly generates a set of facial expressions for multiple character identities and explores the possibilities of generating complex expressions by combining the simple one…
Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifier to misclassify it. In many cases, these modifications can be so subtle that a human observer does not even notice the modification at all, yet the classifier still makes a mistake. Adversarial examples pose security concerns because they could be used to perform an attack on machine learning systems, even if the adversary has no access to the underlying mo…
