AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Adversarial Visual-Instructions

arXiv:2403.09346v1 Announce Type: new
Abstract: Large Vision-Language Models (LVLMs) have shown significant progress in well responding to visual-instructions from users. However, these instructions, encompassing images and text, are susceptible to both intentional and inadvertent attacks. Despite the critical importance of LVLMs' robustness against such threats, current research in this area remains limited. To bridge this gap, we introduce AVIBench, a framework designed to analyze the robustness of LVLMs when facing various adversarial visual-instructions (AVIs), including four types of image-based AVIs, …

abstract adversarial arxiv attacks cs.ai cs.cv current however images importance language language model language models progress research robustness text threats type vision vision-language models visual