Related papers: MultiRobustBench: Benchmarking Robustness Against …

As a research community, we are still lacking a systematic understanding of the progress on adversarial robustness which often makes it hard to identify the most promising ideas in training robust models. A key challenge in benchmarking…

As large language models (LLMs) grow more powerful, ensuring their safety against misuse becomes crucial. While researchers have focused on developing robust defenses, no method has yet achieved complete invulnerability to attacks. We…

As the adoption of machine learning models increases, ensuring robust models against adversarial attacks is increasingly important. With unsupervised machine learning gaining more attention, ensuring it is robust against attacks is vital.…

While adversarial robustness in computer vision is a mature research field, fewer researchers have tackled the evasion attacks against tabular deep learning, and even fewer investigated robustification mechanisms and reliable defenses. We…

Deep neural networks (DNNs) have achieved remarkable performance across a wide range of applications, while they are vulnerable to adversarial examples, which motivates the evaluation and benchmark of model robustness. However, current…

Despite being popularly used in many applications, neural network models have been found to be vulnerable to adversarial examples, i.e., carefully crafted examples aiming to mislead machine learning models. Adversarial examples can pose…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in artificial intelligence by facilitating integrated understanding across diverse modalities, including text, images, video, audio, and speech. However,…

While the literature on security attacks and defense of Machine Learning (ML) systems mostly focuses on unrealistic adversarial examples, recent research has raised concern about the under-explored field of realistic adversarial attacks and…

Recent advances in multi-modal large language models (MLLMs) have enabled unified perception-reasoning capabilities, yet these systems remain highly vulnerable to jailbreak attacks that bypass safety alignment and induce harmful behaviors.…

As deep learning advances, Large Language Models (LLMs) and their multimodal counterparts, Multimodal Large Language Models (MLLMs), have shown exceptional performance in many real-world tasks. However, MLLMs face significant security…

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…

Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of…

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…

With the increasing use of large language models (LLMs), ensuring reliable performance in diverse, real-world environments is essential. Despite their remarkable achievements, LLMs often struggle with adversarial inputs, significantly…

Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers. While most work has defended against a single type of…

Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it is of great significance…

Defenses against adversarial examples, such as adversarial training, are typically tailored to a single perturbation type (e.g., small $\ell_\infty$-noise). For other perturbations, these defenses offer no guarantees and, at times, even…

Multimodal Large Language Models (MLLMs) increasingly support dynamic image resolutions. However, current evaluation paradigms primarily assess semantic performance, overlooking the critical question of resolution robustness - whether…

The increasing deployment of Large Language Models (LLMs) in various applications necessitates a rigorous evaluation of their robustness against adversarial attacks. In this paper, we present a comprehensive study on the robustness of GPT…

Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some…