The advancement of large language models (LLMs) has significantly enhanced the ability to
effectively tackle various downstream NLP tasks and unify these tasks into generative …

Ensuring the safety alignment of Large Language Models (LLMs) is crucial to generating
responses consistent with human values. Despite their ability to recognize and avoid …

Augmenting language models with image inputs may enable more effective jailbreak attacks
through continuous optimization, unlike text inputs that require discrete optimization …

Vision Language Models (VLMs) can produce unintended and harmful content when
exposed to adversarial attacks, particularly because their vision capabilities create new …

Recent studies have revealed the vulnerability of Large Language Models (LLMs) to
adversarial attacks, where the adversary crafts specific input sequences to induce harmful …

This paper investigates the robustness of vision-language models against adversarial visual
perturbations and introduces a novel``double visual defense" to enhance this robustness …

Multimodal Large Language Models (MLLMs), built upon LLMs, have recently gained
attention for their capabilities in image recognition and understanding. However, while …