From 33f19ba5fac3a859c00bbd0c3422beaf2b478b15 Mon Sep 17 00:00:00 2001
From: Daizong Liu <dzliu@stu.pku.edu.cn>
Date: Tue, 11 Mar 2025 15:35:00 +0800
Subject: [PATCH] update 3.11.2025

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

diff --git a/README.md b/README.md
index 0ab1ee1..1ab2aef 100644
--- a/README.md
+++ b/README.md
@@ -279,6 +279,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍.
   * Ziyi Zhang, Zhen Sun, Zongmin Zhang, Jihui Guo, Xinlei He
   * The Hong Kong University of Science and Technology, The University of Hong Kong
   * [Arxiv2025] https://arxiv.org/abs/2502.21059
+* **Utilizing Jailbreak Probability to Attack and Safeguard Multimodal LLMs** |  #
+  * Wenzhuo Xu, Zhipeng Wei, Xiongtao Sun, Deyue Zhang, Dongdong Yang, Quanchen Zou, Xiangzheng Zhang
+  * 360 AI Security Lab, Xidian University
+  * [Arxiv2025] https://arxiv.org/abs/2503.06989
 
 ## Prompt-Injection
 * **Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs** |