From a88cb7206af6a42e2c75e1b501293de8f87f6e36 Mon Sep 17 00:00:00 2001
From: Daizong Liu <dzliu@stu.pku.edu.cn>
Date: Mon, 8 Jul 2024 11:24:52 +0800
Subject: [PATCH] update 7.8.2024

---
 README.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/README.md b/README.md
index 7e29566..af19597 100644
--- a/README.md
+++ b/README.md
@@ -182,6 +182,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍.
   * Zonghao Ying, Aishan Liu, Xianglong Liu, Dacheng Tao
   * Beihang University, Nanyang Technological University
   * [Arxiv2024] https://arxiv.org/abs/2406.06302
+* **Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character** | 
+  * Siyuan Ma, Weidi Luo, Yu Wang, Xiaogeng Liu
+  * University of Wisconsin–Madison, The Ohio State University, Peking University
+  * [Arxiv2024] https://arxiv.org/abs/2405.20773
 
 ## Prompt-Injection
 * **Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs** |