Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models

NeurIPSSpotlight2025

Authors: Xiaowen Cai, Daizong Liu, Xiaoye Qu, Xiang Fang, Jianfeng Dong, Keke Tang, Pan Zhou, Lichao Sun, Wei Hu
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Although Large Vision-Language Models (LVLMs) exhibit impressive multimodal capabilities, their vulnerability to adversarial examples has raised serious security concerns…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

vision-language language model adversarial multimodal

← All NeurIPS 2025 Spotlight papers · Browse the whole archive