From 8f0f3bba30e2c7198f672f29173620706ecaa8d2 Mon Sep 17 00:00:00 2001
From: Daizong Liu <dzliu@stu.pku.edu.cn>
Date: Mon, 8 Jul 2024 11:03:25 +0800
Subject: [PATCH] update 7.8.2024

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

diff --git a/README.md b/README.md
index f7baa27..560e95e 100644
--- a/README.md
+++ b/README.md
@@ -108,6 +108,10 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍.
   * Qi Guo, Shanmin Pang, Xiaojun Jia, Qing Guo
   * Xi’an Jiaotong University, Nanyang Technological University, Center for Frontier AI Research
   * [Arxiv2024] https://arxiv.org/abs/2404.10335
+* **Adversarial Attacks on Multimodal Agents** | 
+  * Chen Henry Wu, Jing Yu Koh, Ruslan Salakhutdinov, Daniel Fried, Aditi Raghunathan
+  * Carnegie Mellon University
+  * [Arxiv2024] https://arxiv.org/abs/2406.12814
 
 ## Jailbreak-Attack
 * **Are aligned neural networks adversarially aligned?** |