相关论文: Confidence-Calibrated Adversarial Training: Genera…

In the scenario of black-box adversarial attack, the target model's parameters are unknown, and the attacker aims to find a successful adversarial perturbation based on query feedback under a query budget. Due to the limited feedback…

While convolutional neural networks (CNNs) have achieved excellent performances in various computer vision tasks, they often misclassify with malicious samples, a.k.a. adversarial examples. Adversarial training is a popular and…

The impact of inference-time data perturbation (e.g., adversarial attacks) has been extensively studied in machine learning, leading to well-established certification techniques for adversarial robustness. In contrast, certifying models…

Ensemble Adversarial Training (EAT) attempts to enhance the robustness of models against adversarial attacks by leveraging multiple models. However, current EAT strategies tend to train the sub-models independently, ignoring the cooperative…

As deep learning models are increasingly deployed in high-risk applications, robust defenses against adversarial attacks and reliable performance guarantees become paramount. Moreover, accuracy alone does not provide sufficient assurance or…

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…

Adversarial training, originally designed to resist test-time adversarial examples, has shown to be promising in mitigating training-time availability attacks. This defense ability, however, is challenged in this paper. We identify a novel…

Adversarial attacks pose significant challenges for vision models in critical fields like healthcare, where reliability is essential. Although adversarial training has been well studied in natural images, its application to biomedical and…

Adversarial training is one of the most effective defenses against adversarial attacks, but it incurs a high computational cost. In this study, we present the first theoretical analysis suggesting that adversarially pretrained transformers…

Adversarial robustness research primarily focuses on L_p perturbations, and most defenses are developed with identical training-time and test-time adversaries. However, in real-world applications developers are unlikely to have access to…

A key challenge in adversarial robustness is the lack of a precise mathematical characterization of human perception, used in the very definition of adversarial attacks that are imperceptible to human eyes. Most current attacks and defenses…

Today's state-of-the-art image classifiers fail to correctly classify carefully manipulated adversarial images. In this work, we develop a new, localized adversarial attack that generates adversarial examples by imperceptibly altering the…

Existing defenses against adversarial examples such as adversarial training typically assume that the adversary will conform to a specific or known threat model, such as $\ell_p$ perturbations within a fixed budget. In this paper, we focus…

Neural networks are getting deeper and more computation-intensive nowadays. Quantization is a useful technique in deploying neural networks on hardware platforms and saving computation costs with negligible performance loss. However, recent…

In Federated Learning (FL), models are as fragile as centrally trained models against adversarial examples. However, the adversarial robustness of federated learning remains largely unexplored. This paper casts light on the challenge of…

Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have…

In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent…

Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense…

Despite extensive diagnostics and debugging by developers, AI systems sometimes exhibit harmful unintended behaviors. Finding and fixing these is challenging because the attack surface is so large -- it is not tractable to exhaustively…

While adversarial training has been extensively studied for ResNet architectures and low resolution datasets like CIFAR, much less is known for ImageNet. Given the recent debate about whether transformers are more robust than convnets, we…