The existence of adversarial examples capable of fooling trained neural network classifiers calls for a much better understanding of possible attacks to guide the development of safeguards against them. This includes attack methods in the challenging non-interactive blackbox setting, where adversarial attacks are generated without any access, including queries, to the target model. Prior attacks in this setting have relied mainly on algorithmic innovations derived from empirical observations (e.g., that momentum helps), lacking principled transferability guarantees. In this work, we provide a theoretical foundation for crafting transferable adversarial examples to entire hypothesis classes. We introduce Adversarial Example Games (AEG), a framework that models the crafting of adversarial examples as a min-max game between a generator of attacks and a classifier. AEG provides a new way to design adversarial examples by adversarially training a generator and a classifier from a given hypothesis class (e.g., architecture). We prove that this game has an equilibrium, and that the optimal generator is able to craft adversarial examples that can attack any classifier from the corresponding hypothesis class. We demonstrate the efficacy of AEG on the MNIST and CIFAR-10 datasets, outperforming prior state-of-the-art approaches with an average relative improvement of $29.9\%$ and $47.2\%$ against undefended and robust models (Table 2 & 3) respectively.
相關內容
Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, a significant generalization gap in the robustness obtained from AT has been problematic, making practitioners to consider a bag of tricks for a successful training, e.g., early stopping. In this paper, we investigate data augmentation (DA) techniques to address the issue. In contrast to the previous reports in the literature that DA is not effective for regularizing AT, we discover that DA can mitigate overfitting in AT surprisingly well, but they should be chosen deliberately. To utilize the effect of DA further, we propose a simple yet effective auxiliary 'consistency' regularization loss to optimize, which forces predictive distributions after attacking from two different augmentations to be similar to each other. Our experimental results demonstrate that our simple regularization scheme is applicable for a wide range of AT methods, showing consistent yet significant improvements in the test robust accuracy. More remarkably, we also show that our method could significantly help the model to generalize its robustness against unseen adversaries, e.g., other types or larger perturbations compared to those used during training. Code is available at //github.com/alinlab/consistency-adversarial.
Studies show that neural networks are susceptible to adversarial attacks. This exposes a potential threat to neural network-based artificial intelligence systems. We observe that the probability of the correct result outputted by the neural network increases by applying small perturbations generated for non-predicted class labels to adversarial examples. Based on this observation, we propose a method of counteracting adversarial perturbations to resist adversarial examples. In our method, we randomly select a number of class labels and generate small perturbations for these selected labels. The generated perturbations are added together and then clamped onto a specified space. The obtained perturbation is finally added to the adversarial example to counteract the adversarial perturbation contained in the example. The proposed method is applied at inference time and does not require retraining or finetuning the model. We validate the proposed method on CIFAR-10 and CIFAR-100. The experimental results demonstrate that our method effectively improves the defense performance of the baseline methods, especially against strong adversarial examples generated using more iterations.
We introduce two challenging datasets that reliably cause machine learning model performance to substantially degrade. The datasets are collected with a simple adversarial filtration technique to create datasets with limited spurious cues. Our datasets' real-world, unmodified examples transfer to various unseen models reliably, demonstrating that computer vision models have shared weaknesses. The first dataset is called ImageNet-A and is like the ImageNet test set, but it is far more challenging for existing models. We also curate an adversarial out-of-distribution detection dataset called ImageNet-O, which is the first out-of-distribution detection dataset created for ImageNet models. On ImageNet-A a DenseNet-121 obtains around 2% accuracy, an accuracy drop of approximately 90%, and its out-of-distribution detection performance on ImageNet-O is near random chance levels. We find that existing data augmentation techniques hardly boost performance, and using other public training datasets provides improvements that are limited. However, we find that improvements to computer vision architectures provide a promising path towards robust 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.
There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack. We present a new approach towards ending this cycle where we "deflect'' adversarial attacks by causing the attacker to produce an input that semantically resembles the attack's target class. To this end, we first propose a stronger defense based on Capsule Networks that combines three detection mechanisms to achieve state-of-the-art detection performance on both standard and defense-aware attacks. We then show that undetected attacks against our defense often perceptually resemble the adversarial target class by performing a human study where participants are asked to label images produced by the attack. These attack images can no longer be called "adversarial'' because our network classifies them the same way as humans do.
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.
Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which leverages clean and adversarial samples to optimize the initialization of a learning model in an adversarial manner. ADML leads to the following desirable properties: 1) it turns out to be very effective even in the cases with only clean samples; 2) it is model-agnostic, i.e., it is compatible with any learning model that can be trained with gradient descent; and most importantly, 3) it is robust to adversarial samples, i.e., unlike other meta-learning methods, it only leads to a minor performance degradation when there are adversarial samples. We show via extensive experiments that ADML delivers the state-of-the-art performance on two widely-used image datasets, MiniImageNet and CIFAR100, in terms of both accuracy and robustness.
We introduce an effective model to overcome the problem of mode collapse when training Generative Adversarial Networks (GAN). Firstly, we propose a new generator objective that finds it better to tackle mode collapse. And, we apply an independent Autoencoders (AE) to constrain the generator and consider its reconstructed samples as "real" samples to slow down the convergence of discriminator that enables to reduce the gradient vanishing problem and stabilize the model. Secondly, from mappings between latent and data spaces provided by AE, we further regularize AE by the relative distance between the latent and data samples to explicitly prevent the generator falling into mode collapse setting. This idea comes when we find a new way to visualize the mode collapse on MNIST dataset. To the best of our knowledge, our method is the first to propose and apply successfully the relative distance of latent and data samples for stabilizing GAN. Thirdly, our proposed model, namely Generative Adversarial Autoencoder Networks (GAAN), is stable and has suffered from neither gradient vanishing nor mode collapse issues, as empirically demonstrated on synthetic, MNIST, MNIST-1K, CelebA and CIFAR-10 datasets. Experimental results show that our method can approximate well multi-modal distribution and achieve better results than state-of-the-art methods on these benchmark datasets. Our model implementation is published here: //github.com/tntrung/gaan
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.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191