Xin-Jue Hu

EGP-Defense: Enhancing Adversarial Robustness of LVLMs via Training-Free Edge-Guided Prompting

Large Vision-Language Models (LVLMs) have demonstrated remarkable multimodal comprehension capabilities, achieving state-of-the-art performance across various vision-language tasks. However, their performance drops significantly when facing adversarial attacks on the visual encoder. To alleviate this issue, existing ap...