From 33573f49a873ea08580ddb5a5299b9c8de53f62d Mon Sep 17 00:00:00 2001 From: Daizong Liu Date: Tue, 20 May 2025 15:28:47 +0800 Subject: [PATCH] update 5.20.2025 --- README.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/README.md b/README.md index 9787a6b..e2d7866 100644 --- a/README.md +++ b/README.md @@ -311,6 +311,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍. * Yi Nian, Shenzhe Zhu, Yuehan Qin, Li Li, Ziyi Wang, Chaowei Xiao, Yue Zhao * University of Southern California, University of Toronto, University of Maryland, University of Wisconsin-Madison * [Arxiv2025] https://arxiv.org/abs/2504.03770 +* **BadNAVer: Exploring Jailbreak Attacks On Vision-and-Language Navigation** | # + * Wenqi Lyu, Zerui Li, Yanyuan Qiao, Qi Wu + * University of Adelaide + * [Arxiv2025] https://arxiv.org/abs/2505.12443 ## Prompt-Injection * **Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs** | @@ -365,6 +369,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍. * Le Wang, Zonghao Ying, Tianyuan Zhang, Siyuan Liang, Shengshan Hu, Mingchuan Zhang, Aishan Liu, Xianglong Liu * Beihang University, National University of Singapore, Huazhong University of Science and Technology, Henan University of Science and Technology * [Arxiv2025] https://arxiv.org/abs/2504.14348 +* **EnvInjection: Environmental Prompt Injection Attack to Multi-modal Web Agents** | # + * Xilong Wang, John Bloch, Zedian Shao, Yuepeng Hu, Shuyan Zhou, Neil Zhenqiang Gong + * Duke University + * [Arxiv2025] https://arxiv.org/abs/2505.11717 ## Data-Poisoning * **Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models** | [Github](https://github.com/umd-huang-lab/VLM-Poisoning)