From 54529924b6fef0d9ad54a40ba0d57fa76fd1f8f1 Mon Sep 17 00:00:00 2001
From: Daizong Liu <dzliu@stu.pku.edu.cn>
Date: Fri, 23 May 2025 23:37:19 +0800
Subject: [PATCH] update 5.23.2025

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

diff --git a/README.md b/README.md
index e2d7866..f1fe942 100644
--- a/README.md
+++ b/README.md
@@ -315,6 +315,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍.
   * Wenqi Lyu, Zerui Li, Yanyuan Qiao, Qi Wu
   * University of Adelaide
   * [Arxiv2025] https://arxiv.org/abs/2505.12443
+* **Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models** |  #
+  * Zhaoxin Wang, Handing Wang, Cong Tian, Yaochu Jin
+  * Xidian University, Westlake University
+  * [Arxiv2025] https://arxiv.org/abs/2505.16446
 
 ## Prompt-Injection
 * **Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs** |