From 1028d0314228c57f6d58e03cecd62bca3f92696e Mon Sep 17 00:00:00 2001
From: Daizong Liu <dzliu@stu.pku.edu.cn>
Date: Tue, 3 Dec 2024 10:22:30 +0800
Subject: [PATCH] update 12.3.2024

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

diff --git a/README.md b/README.md
index fd1cc34..6adb9e4 100644
--- a/README.md
+++ b/README.md
@@ -234,6 +234,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍.
   * Tiejin Chen, Kaishen Wang, Hua Wei
   * Arizona State University
   * [Arxiv2024] https://arxiv.org/abs/2411.07559
+* **Jailbreak Large Visual Language Models Through Multi-Modal Linkage** | [Github](https://github.com/wangyu-ovo/MML) #
+  * Yu Wang, Xiaofei Zhou, Yichen Wang, Geyuan Zhang, Tianxing He
+  * 
+  * [Arxiv2024] https://arxiv.org/abs/2412.00473
 
 ## Prompt-Injection
 * **Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs** |