In spite of intense research efforts, deep neural networks remain vulnerable to adversarial examples: an input that forces the network to confidently produce incorrect outputs. Adversarial examples are typically generated by an attack algorithm that optimizes a perturbation added to a benign input. Many such algorithms have been developed. If it were possible to reverse engineer attack algorithms from adversarial examples, this could deter bad actors because of the possibility of attribution. Here we formulate reverse engineering as a supervised learning problem where the goal is to assign an adversarial example to a class that represents the algorithm and parameters used. To our knowledge it has not been previously shown whether this is even possible. We first test whether we can classify the perturbations added to images by attacks on undefended single-label image classification models. Taking a "fight fire with fire" approach, we leverage the sensitivity of deep neural networks to adversarial examples, training them to classify these perturbations. On a 17-class dataset (5 attacks, 4 bounded with 4 epsilon values each), we achieve an accuracy of 99.4% with a ResNet50 model trained on the perturbations. We then ask whether we can perform this task without access to the perturbations, obtaining an estimate of them with signal processing algorithms, an approach we call "fingerprinting". We find the JPEG algorithm serves as a simple yet effective fingerprinter (85.05% accuracy), providing a strong baseline for future work. We discuss how our approach can be extended to attack agnostic, learnable fingerprints, and to open-world scenarios with unknown attacks.
相關內容
Adversarial examples are crafted by adding indistinguishable perturbations to normal examples in order to fool a well-trained deep learning model to misclassify. In the context of computer vision, this notion of indistinguishability is typically bounded by $L_{\infty}$ or other norms. However, these norms are not appropriate for measuring indistinguishiability for time series data. In this work, we propose adversarial examples in the Wasserstein space for time series data for the first time and utilize Wasserstein distance to bound the perturbation between normal examples and adversarial examples. We introduce Wasserstein projected gradient descent (WPGD), an adversarial attack method for perturbing univariant time series data. We leverage the closed-form solution of Wasserstein distance in the 1D space to calculate the projection step of WPGD efficiently with the gradient descent method. We further propose a two-step projection so that the search of adversarial examples in the Wasserstein space is guided and constrained by Euclidean norms to yield more effective and imperceptible perturbations. We empirically evaluate the proposed attack on several time series datasets in the healthcare domain. Extensive results demonstrate that the Wasserstein attack is powerful and can successfully attack most of the target classifiers with a high attack success rate. To better study the nature of Wasserstein adversarial example, we evaluate a strong defense mechanism named Wasserstein smoothing for potential certified robustness defense. Although the defense can achieve some accuracy gain, it still has limitations in many cases and leaves space for developing a stronger certified robustness method to Wasserstein adversarial examples on univariant time series data.
Adversarial attacks can mislead deep learning models to make false predictions by implanting small perturbations to the original input that are imperceptible to the human eye, which poses a huge security threat to the computer vision systems based on deep learning. Physical adversarial attacks, which is more realistic, as the perturbation is introduced to the input before it is being captured and converted to a binary image inside the vision system, when compared to digital adversarial attacks. In this paper, we focus on physical adversarial attacks and further classify them into invasive and non-invasive. Optical-based physical adversarial attack techniques (e.g. using light irradiation) belong to the non-invasive category. As the perturbations can be easily ignored by humans as the perturbations are very similar to the effects generated by a natural environment in the real world. They are highly invisibility and executable and can pose a significant or even lethal threats to real systems. This paper focuses on optical-based physical adversarial attack techniques for computer vision systems, with emphasis on the introduction and discussion of optical-based physical adversarial attack techniques.
Machine learning models have made many decision support systems to be faster, more accurate, and more efficient. However, applications of machine learning in network security face a more disproportionate threat of active adversarial attacks compared to other domains. This is because machine learning applications in network security such as malware detection, intrusion detection, and spam filtering are by themselves adversarial in nature. In what could be considered an arm's race between attackers and defenders, adversaries constantly probe machine learning systems with inputs that are explicitly designed to bypass the system and induce a wrong prediction. In this survey, we first provide a taxonomy of machine learning techniques, tasks, and depth. We then introduce a classification of machine learning in network security applications. Next, we examine various adversarial attacks against machine learning in network security and introduce two classification approaches for adversarial attacks in network security. First, we classify adversarial attacks in network security based on a taxonomy of network security applications. Secondly, we categorize adversarial attacks in network security into a problem space vs feature space dimensional classification model. We then analyze the various defenses against adversarial attacks on machine learning-based network security applications. We conclude by introducing an adversarial risk grid map and evaluating several existing adversarial attacks against machine learning in network security using the risk grid map. We also identify where each attack classification resides within the adversarial risk grid map.
We perform a set of experiments to demonstrate that images generated using a Generative Adversarial Network can be modified using 'semiotics.' We show that just as physical attributes such as the hue and saturation of an image can be modified, so too can its non-physical, abstract properties using our method. For example, the design of a flight attendant's uniform may be modified to look more 'alert,' less 'austere,' or more 'practical.' The form of a house can be modified to appear more 'futuristic,' a car more 'friendly' a pair of sneakers, 'evil.' Our method uncovers latent visual iconography associated with the semiotic property of interest, enabling a process of visual form-finding using abstract concepts. Our approach is iterative and allows control over the degree of attribute presence and can be used to aid the design process to yield emergent visual concepts.
Knowledge graphs represent factual knowledge about the world as relationships between concepts and are critical for intelligent decision making in enterprise applications. New knowledge is inferred from the existing facts in the knowledge graphs by encoding the concepts and relations into low-dimensional feature vector representations. The most effective representations for this task, called Knowledge Graph Embeddings (KGE), are learned through neural network architectures. Due to their impressive predictive performance, they are increasingly used in high-impact domains like healthcare, finance and education. However, are the black-box KGE models adversarially robust for use in domains with high stakes? This thesis argues that state-of-the-art KGE models are vulnerable to data poisoning attacks, that is, their predictive performance can be degraded by systematically crafted perturbations to the training knowledge graph. To support this argument, two novel data poisoning attacks are proposed that craft input deletions or additions at training time to subvert the learned model's performance at inference time. These adversarial attacks target the task of predicting the missing facts in knowledge graphs using KGE models, and the evaluation shows that the simpler attacks are competitive with or outperform the computationally expensive ones. The thesis contributions not only highlight and provide an opportunity to fix the security vulnerabilities of KGE models, but also help to understand the black-box predictive behaviour of KGE models.
Adversarial attack is a technique for deceiving Machine Learning (ML) models, which provides a way to evaluate the adversarial robustness. In practice, attack algorithms are artificially selected and tuned by human experts to break a ML system. However, manual selection of attackers tends to be sub-optimal, leading to a mistakenly assessment of model security. In this paper, a new procedure called Composite Adversarial Attack (CAA) is proposed for automatically searching the best combination of attack algorithms and their hyper-parameters from a candidate pool of \textbf{32 base attackers}. We design a search space where attack policy is represented as an attacking sequence, i.e., the output of the previous attacker is used as the initialization input for successors. Multi-objective NSGA-II genetic algorithm is adopted for finding the strongest attack policy with minimum complexity. The experimental result shows CAA beats 10 top attackers on 11 diverse defenses with less elapsed time (\textbf{6 $\times$ faster than AutoAttack}), and achieves the new state-of-the-art on $l_{\infty}$, $l_{2}$ and unrestricted adversarial attacks.
While existing work in robust deep learning has focused on small pixel-level $\ell_p$ norm-based perturbations, this may not account for perturbations encountered in several real world settings. In many such cases although test data might not be available, broad specifications about the types of perturbations (such as an unknown degree of rotation) may be known. We consider a setup where robustness is expected over an unseen test domain that is not i.i.d. but deviates from the training domain. While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes. We propose an adversarial training approach which learns to generate new samples so as to maximize exposure of the classifier to the attributes-space, without having access to the data from the test domain. Our adversarial training solves a min-max optimization problem, with the inner maximization generating adversarial perturbations, and the outer minimization finding model parameters by optimizing the loss on adversarial perturbations generated from the inner maximization. We demonstrate the applicability of our approach on three types of naturally occurring perturbations -- object-related shifts, geometric transformations, and common image corruptions. Our approach enables deep neural networks to be robust against a wide range of naturally occurring perturbations. We demonstrate the usefulness of the proposed approach by showing the robustness gains of deep neural networks trained using our adversarial training on MNIST, CIFAR-10, and a new variant of the CLEVR dataset.
Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i.e., images, graphs and text.
Adversarial attacks to image classification systems present challenges to convolutional networks and opportunities for understanding them. This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks. Motivated by this observation, we develop new network architectures that increase adversarial robustness by performing feature denoising. Specifically, our networks contain blocks that denoise the features using non-local means or other filters; the entire networks are trained end-to-end. When combined with adversarial training, our feature denoising networks substantially improve the state-of-the-art in adversarial robustness in both white-box and black-box attack settings. On ImageNet, under 10-iteration PGD white-box attacks where prior art has 27.9% accuracy, our method achieves 55.7%; even under extreme 2000-iteration PGD white-box attacks, our method secures 42.6% accuracy. A network based on our method was ranked first in Competition on Adversarial Attacks and Defenses (CAAD) 2018 --- it achieved 50.6% classification accuracy on a secret, ImageNet-like test dataset against 48 unknown attackers, surpassing the runner-up approach by ~10%. Code and models will be made publicly available.
There is a recent large and growing interest in generative adversarial networks (GANs), which offer powerful features for generative modeling, density estimation, and energy function learning. GANs are difficult to train and evaluate but are capable of creating amazingly realistic, though synthetic, image data. Ideas stemming from GANs such as adversarial losses are creating research opportunities for other challenges such as domain adaptation. In this paper, we look at the field of GANs with emphasis on these areas of emerging research. To provide background for adversarial techniques, we survey the field of GANs, looking at the original formulation, training variants, evaluation methods, and extensions. Then we survey recent work on transfer learning, focusing on comparing different adversarial domain adaptation methods. Finally, we take a look forward to identify open research directions for GANs and domain adaptation, including some promising applications such as sensor-based human behavior modeling.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191