From bc32382cd6035e0224e50ffddf23db5a97379482 Mon Sep 17 00:00:00 2001 From: Daizong Liu Date: Wed, 25 Dec 2024 16:58:17 +0800 Subject: [PATCH] update 12.25.2024 --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index ebf7878..374ac56 100644 --- a/README.md +++ b/README.md @@ -246,6 +246,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍. * Ma Teng, Jia Xiaojun, Duan Ranjie, Li Xinfeng, Huang Yihao, Chu Zhixuan, Liu Yang, Ren Wenqi * Sun Yat-Sen University, Nanyang Technological University, Alibaba Group, Zhejiang University * [Arxiv2024] https://arxiv.org/abs/2412.05934 +* **Retention Score: Quantifying Jailbreak Risks for Vision Language Models** | # + * Zaitang Li, Pin-Yu Chen, Tsung-Yi Ho + * The Chinese University of Hong Kong, IBM Research + * [AAAI2025] https://arxiv.org/abs/2412.17544 ## Prompt-Injection * **Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs** |