相关论文: S2O: Enhancing Adversarial Training with Second-Or…

Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve robustness to worst-case distribution shifts caused by…

Adversarial training has been actively studied in recent computer vision research to improve the robustness of models. However, due to the huge computational cost of generating adversarial samples, adversarial training methods are often…

Neural networks are vulnerable to adversarial attacks: adding well-crafted, imperceptible perturbations to their input can modify their output. Adversarial training is one of the most effective approaches in training robust models against…

Adversarial training and its variants have become de facto standards for learning robust deep neural networks. In this paper, we explore the landscape around adversarial training in a bid to uncover its limits. We systematically study the…

The vulnerability of deep neural networks against adversarial examples - inputs with small imperceptible perturbations - has gained a lot of attention in the research community recently. Simultaneously, the number of parameters of…

Deep Neural Networks are vulnerable to adversarial attacks even in settings where the attacker has no direct access to the model being attacked. Such attacks usually rely on the principle of transferability, whereby an attack crafted on a…

Adversarial training, especially projected gradient descent (PGD), has proven to be a successful approach for improving robustness against adversarial attacks. After adversarial training, gradients of models with respect to their inputs…

While existing work in robust deep learning has focused on small pixel-level 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…

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…

An acknowledged weakness of neural networks is their vulnerability to adversarial perturbations to the inputs. To improve the robustness of these models, one of the most popular defense mechanisms is to alternatively maximize the loss over…

Weight averaging is a widely used technique for accelerating training and improving the generalization of deep neural networks (DNNs). While existing approaches like stochastic weight averaging (SWA) rely on pre-set weighting schemes, they…

It has been shown that deep neural networks (DNNs) may be vulnerable to adversarial attacks, raising the concern on their robustness particularly for safety-critical applications. Recognizing the local nature and limitations of existing…

Adversarial training improves the robustness of neural networks against adversarial attacks, albeit at the expense of the trade-off between standard and robust generalization. To unveil the underlying factors driving this phenomenon, we…

Cost-sensitive classification is critical in applications where misclassification errors widely vary in cost. However, over-parameterization poses fundamental challenges to the cost-sensitive modeling of deep neural networks (DNNs). The…

We present a new algorithm to learn a deep neural network model robust against adversarial attacks. Previous algorithms demonstrate an adversarially trained Bayesian Neural Network (BNN) provides improved robustness. We recognize the…

Adversarial robustness has become an emerging challenge for neural network owing to its over-sensitivity to small input perturbations. While being critical, we argue that solving this singular issue alone fails to provide a comprehensive…

Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples. While numerous successful adversarial attacks have been proposed, defenses against these attacks remain relatively understudied. Existing defense…

Despite a great deal of research, it is still not well-understood why trained neural networks are highly vulnerable to adversarial examples. In this work we focus on two-layer neural networks trained using data which lie on a low…

Adversarial training can improve the robustness of neural networks. Previous methods focus on a single adversarial training strategy and do not consider the model property trained by different strategies. By revisiting the previous methods,…

In the last a few decades, deep neural networks have achieved remarkable success in machine learning, computer vision, and pattern recognition. Recent studies however show that neural networks (both shallow and deep) may be easily fooled by…