Related papers: Fast Adversarial Training with Adaptive Step Size
Despite their overwhelming success on a wide range of applications, convolutional neural networks (CNNs) are widely recognized to be vulnerable to adversarial examples. This intriguing phenomenon led to a competition between adversarial…
Instances-reweighted adversarial training (IRAT) can significantly boost the robustness of trained models, where data being less/more vulnerable to the given attack are assigned smaller/larger weights during training. However, when tested…
Adversarial learning methods are a promising approach to training robust deep networks, and can generate complex samples across diverse domains. They also can improve recognition despite the presence of domain shift or dataset bias: several…
Single-step adversarial training (SSAT) has demonstrated the potential to achieve both efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a phenomenon that leads to a severely distorted classifier, making…
Deep learning models continue to advance in accuracy, yet they remain vulnerable to adversarial attacks, which often lead to the misclassification of adversarial examples. Adversarial training is used to mitigate this problem by increasing…
In this work, we propose new adaptive step size strategies that improve several stochastic gradient methods. Our first method (StoPS) is based on the classical Polyak step size (Polyak, 1987) and is an extension of the recent development of…
Whereas adversarial training can be useful against specific adversarial perturbations, they have also proven ineffective in generalizing towards attacks deviating from those used for training. However, we observe that this ineffectiveness…
This paper presents GReAT (Graph Regularized Adversarial Training), a novel regularization method designed to enhance the robust classification performance of deep learning models. Adversarial examples, characterized by subtle perturbations…
Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness. However, we observe that a too large number of search steps can hurt accuracy. We…
Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack…
DL-based automatic modulation classification (AMC) models are highly susceptible to adversarial attacks, where even minimal input perturbations can cause severe misclassifications. While adversarially training an AMC model based on an…
Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite contributing…
Despite its remarkable success in zero-shot image-text matching, CLIP remains highly vulnerable to adversarial perturbations on images. As adversarial fine-tuning is prohibitively costly, recent works explore various test-time defense…
Fast Adversarial Training (FAT) has gained increasing attention within the research community owing to its efficacy in improving adversarial robustness. Particularly noteworthy is the challenge posed by catastrophic overfitting (CO) in this…
Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations. However, most defense mechanisms only consider a single type of perturbation while various attack methods might be…
Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on both heuristics-driven and data-driven augmentations as a means to reduce…
Adversarial Training (AT) is one of the most effective methods for developing robust deep neural networks (DNNs). However, AT faces a trade-off problem between clean accuracy and adversarial robustness. In this work, we reveal a surprising…
With the increasing amount of available data and advances in computing capabilities, deep neural networks (DNNs) have been successfully employed to solve challenging tasks in various areas, including healthcare, climate, and finance.…
Recently demonstrated physical-world adversarial attacks have exposed vulnerabilities in perception systems that pose severe risks for safety-critical applications such as autonomous driving. These attacks place adversarial artifacts in the…
Adaptive gradient algorithms perform gradient-based updates using the history of gradients and are ubiquitous in training deep neural networks. While adaptive gradient methods theory is well understood for minimization problems, the…