相关论文: AttackBench: Evaluating Gradient-based Attacks for…

Over the past decade, U-Net has been the dominant architecture in medical image segmentation, leading to the development of thousands of U-shaped variants. Despite its widespread adoption, there is still no comprehensive benchmark to…

Graph neural networks, a popular class of models effective in a wide range of graph-based learning tasks, have been shown to be vulnerable to adversarial attacks. While the majority of the literature focuses on such vulnerability in…

We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient…

Deep neural networks (DNNs) are vulnerable to adversarial examples obtained by adding small perturbations to original examples. The added perturbations in existing attacks are mainly determined by the gradient of the loss function with…

Although adversarial robustness has been extensively studied in white-box settings, recent advances in black-box attacks (including transfer- and query-based approaches) are primarily benchmarked against weak defenses, leaving a significant…

We introduce AutoAdvExBench, a benchmark to evaluate if large language models (LLMs) can autonomously exploit defenses to adversarial examples. Unlike existing security benchmarks that often serve as proxies for real-world tasks, bench…

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment. Automatic reverse engineering of the toolchains behind these adversarial machine learning attacks will aid in…

Adversarial attacks for image classification are small perturbations to images that are designed to cause misclassification by a model. Adversarial attacks formally correspond to an optimization problem: find a minimum norm image…

Recent years have seen a proliferation of research on adversarial machine learning. Numerous papers demonstrate powerful algorithmic attacks against a wide variety of machine learning (ML) models, and numerous other papers propose defenses…

The problem of attacks on neural networks through input modification (i.e., adversarial examples) has attracted much attention recently. Being relatively easy to generate and hard to detect, these attacks pose a security breach that many…

Enhancing our understanding of adversarial examples is crucial for the secure application of machine learning models in real-world scenarios. A prevalent method for analyzing adversarial examples is through a frequency-based approach.…

State-of-the-art adversarial attacks are aimed at neural network classifiers. By default, neural networks use gradient descent to minimize their loss function. The gradient of a classifier's loss function is used by gradient-based…

Recent studies have shown that the training samples can be recovered from gradients, which are called Gradient Inversion (GradInv) attacks. However, there remains a lack of extensive surveys covering recent advances and thorough analysis of…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Jailbreak attacks represent one of the most sophisticated threats to the security of large language models (LLMs). To deal with such risks, we introduce an innovative framework that can help evaluate the effectiveness of jailbreak attacks…

We introduce a grey-box adversarial attack and defence framework for sentiment classification. We address the issues of differentiability, label preservation and input reconstruction for adversarial attack and defence in one unified…

We present BadGD, a unified theoretical framework that exposes the vulnerabilities of gradient descent algorithms through strategic backdoor attacks. Backdoor attacks involve embedding malicious triggers into a training dataset to disrupt…

Generating adversarial examples at scale is a core primitive for robustness evaluation, adversarial training, and red-teaming, yet even "fast" attacks such as FGSM remain throughput-limited by the cost of a backward pass. We introduce a…

Recently, deep neural networks have significant progress and successful application in various fields, but they are found vulnerable to attack instances, e.g., adversarial examples. State-of-art attack methods can generate attack images by…