Applications of machine learning (ML) models and convolutional neural networks (CNNs) have been rapidly increased. Although state-of-the-art CNNs provide high accuracy in many applications, recent investigations show that such networks are highly vulnerable to adversarial attacks. The black-box adversarial attack is one type of attack that the attacker does not have any knowledge about the model or the training dataset, but it has some input data set and their labels. In this paper, we propose a novel approach to generate a black-box attack in sparse domain whereas the most important information of an image can be observed. Our investigation shows that large sparse (LaS) components play a critical role in the performance of image classifiers. Under this presumption, to generate adversarial example, we transfer an image into a sparse domain and put a threshold to choose only k LaS components. In contrast to the very recent works that randomly perturb k low frequency (LoF) components, we perturb k LaS components either randomly (query-based) or in the direction of the most correlated sparse signal from a different class. We show that LaS components contain some middle or higher frequency components information which leads fooling image classifiers with a fewer number of queries. We demonstrate the effectiveness of this approach by fooling six state-of-the-art image classifiers, the TensorFlow Lite (TFLite) model of Google Cloud Vision platform, and YOLOv5 model as an object detection algorithm. Mean squared error (MSE) and peak signal to noise ratio (PSNR) are used as quality metrics. We also present a theoretical proof to connect these metrics to the level of perturbation in the sparse domain.
相關內容
While adversarial attacks on deep image classification models pose serious security concerns in practice, this paper suggests a novel paradigm where the concept of adversarial attacks can benefit classification performance, which we call amicable aid. We show that by taking the opposite search direction of perturbation, an image can be converted to another yielding higher confidence by the classification model and even a wrongly classified image can be made to be correctly classified. Furthermore, with a large amount of perturbation, an image can be made unrecognizable by human eyes, while it is correctly recognized by the model. The mechanism of the amicable aid is explained in the viewpoint of the underlying natural image manifold. We also consider universal amicable perturbations, i.e., a fixed perturbation can be applied to multiple images to improve their classification results. While it is challenging to find such perturbations, we show that making the decision boundary as perpendicular to the image manifold as possible via training with modified data is effective to obtain a model for which universal amicable perturbations are more easily found. Finally, we discuss several application scenarios where the amicable aid can be useful, including secure image communication, privacy-preserving image communication, and protection against adversarial attacks.
Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we explore how shape bias can be incorporated into CNNs to improve their robustness. Two algorithms are proposed, based on the observation that edges are invariant to moderate imperceptible perturbations. In the first one, a classifier is adversarially trained on images with the edge map as an additional channel. At inference time, the edge map is recomputed and concatenated to the image. In the second algorithm, a conditional GAN is trained to translate the edge maps, from clean and/or perturbed images, into clean images. Inference is done over the generated image corresponding to the input's edge map. Extensive experiments over 10 datasets demonstrate the effectiveness of the proposed algorithms against FGSM and $\ell_\infty$ PGD-40 attacks. Further, we show that a) edge information can also benefit other adversarial training methods, and b) CNNs trained on edge-augmented inputs are more robust against natural image corruptions such as motion blur, impulse noise and JPEG compression, than CNNs trained solely on RGB images. From a broader perspective, our study suggests that CNNs do not adequately account for image structures that are crucial for robustness. Code is available at:~\url{//github.com/aliborji/Shapedefense.git}.
Due to their massive success in various domains, deep learning techniques are increasingly used to design network intrusion detection solutions that detect and mitigate unknown and known attacks with high accuracy detection rates and minimal feature engineering. However, it has been found that deep learning models are vulnerable to data instances that can mislead the model to make incorrect classification decisions so-called (adversarial examples). Such vulnerability allows attackers to target NIDSs by adding small crafty perturbations to the malicious traffic to evade detection and disrupt the system's critical functionalities. The problem of deep adversarial learning has been extensively studied in the computer vision domain; however, it is still an area of open research in network security applications. Therefore, this survey explores the researches that employ different aspects of adversarial machine learning in the area of network intrusion detection in order to provide directions for potential solutions. First, the surveyed studies are categorized based on their contribution to generating adversarial examples, evaluating the robustness of ML-based NIDs towards adversarial examples, and defending these models against such attacks. Second, we highlight the characteristics identified in the surveyed research. Furthermore, we discuss the applicability of the existing generic adversarial attacks for the NIDS domain, the feasibility of launching the proposed attacks in real-world scenarios, and the limitations of the existing mitigation solutions.
Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning attacks really questions the robustness of ML models. For instance, Engstrom et al. demonstrated that state-of-the-art image classifiers could be easily fooled by a small rotation on an arbitrary image. As ML systems are being increasingly integrated into safety and security-sensitive applications, adversarial attacks and data poisoning attacks pose a considerable threat. This chapter focuses on the two broad and important areas of ML security: adversarial attacks and data poisoning attacks.
Deep neural networks are vulnerable to adversarial examples that mislead the models with imperceptible perturbations. Though adversarial attacks have achieved incredible success rates in the white-box setting, most existing adversaries often exhibit weak transferability in the black-box setting, especially under the scenario of attacking models with defense mechanisms. In this work, we propose a new method called variance tuning to enhance the class of iterative gradient based attack methods and improve their attack transferability. Specifically, at each iteration for the gradient calculation, instead of directly using the current gradient for the momentum accumulation, we further consider the gradient variance of the previous iteration to tune the current gradient so as to stabilize the update direction and escape from poor local optima. Empirical results on the standard ImageNet dataset demonstrate that our method could significantly improve the transferability of gradient-based adversarial attacks. Besides, our method could be used to attack ensemble models or be integrated with various input transformations. Incorporating variance tuning with input transformations on iterative gradient-based attacks in the multi-model setting, the integrated method could achieve an average success rate of 90.1% against nine advanced defense methods, improving the current best attack performance significantly by 85.1% . Code is available at //github.com/JHL-HUST/VT.
Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e., dependency from the target to the source), which is crucial to the tightness of the variational information maximization lower bound. In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target. Within this framework, the forward and backward networks are able to iteratively promote or demote each other's generated instances by comparing the real and synthetic data distributions. We also develop a latent noise sampling strategy that leverages random variations at the high-level semantic space to enhance the long term dependency in the generation process. Extensive experiments based on different text generation tasks demonstrate that the proposed AMI framework can significantly outperform several strong baselines, and we also show that AMI has potential to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem.
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 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 that have negative log-likelihood under the generative model exceeding a threshold pre-specified using training data. Experimental results suggest that deep Bayes classifiers are more robust than deep discriminative classifiers, and the proposed detection methods achieve high detection rates against many recently proposed attacks.
Recently introduced generative adversarial network (GAN) has been shown numerous promising results to generate realistic samples. The essential task of GAN is to control the features of samples generated from a random distribution. While the current GAN structures, such as conditional GAN, successfully generate samples with desired major features, they often fail to produce detailed features that bring specific differences among samples. To overcome this limitation, here we propose a controllable GAN (ControlGAN) structure. By separating a feature classifier from a discriminator, the generator of ControlGAN is designed to learn generating synthetic samples with the specific detailed features. Evaluated with multiple image datasets, ControlGAN shows a power to generate improved samples with well-controlled features. Furthermore, we demonstrate that ControlGAN can generate intermediate features and opposite features for interpolated and extrapolated input labels that are not used in the training process. It implies that ControlGAN can significantly contribute to the variety of generated samples.
Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. Such adversarial examples can mislead DNNs to produce adversary-selected results. Different attack strategies have been proposed to generate adversarial examples, but how to produce them with high perceptual quality and more efficiently requires more research efforts. In this paper, we propose AdvGAN to generate adversarial examples with generative adversarial networks (GANs), which can learn and approximate the distribution of original instances. For AdvGAN, once the generator is trained, it can generate adversarial perturbations efficiently for any instance, so as to potentially accelerate adversarial training as defenses. We apply AdvGAN in both semi-whitebox and black-box attack settings. In semi-whitebox attacks, there is no need to access the original target model after the generator is trained, in contrast to traditional white-box attacks. In black-box attacks, we dynamically train a distilled model for the black-box model and optimize the generator accordingly. Adversarial examples generated by AdvGAN on different target models have high attack success rate under state-of-the-art defenses compared to other attacks. Our attack has placed the first with 92.76% accuracy on a public MNIST black-box attack challenge.
Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence. Early attempts at explaining this phenomenon focused on nonlinearity and overfitting. We argue instead that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature. This explanation is supported by new quantitative results while giving the first explanation of the most intriguing fact about them: their generalization across architectures and training sets. Moreover, this view yields a simple and fast method of generating adversarial examples. Using this approach to provide examples for adversarial training, we reduce the test set error of a maxout network on the MNIST dataset.
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