From 555ca33c1a8c9e800e7af33f3e59fdf9be01ead7 Mon Sep 17 00:00:00 2001
From: Daizong Liu <dzliu@stu.pku.edu.cn>
Date: Sun, 15 Sep 2024 21:47:34 +0800
Subject: [PATCH] update

---
 README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/README.md b/README.md
index 096b0b2..1077887 100644
--- a/README.md
+++ b/README.md
@@ -26,6 +26,9 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍.
 - [Jailbreack Attacks](#Jailbreack-Attack)
 - [Prompt Injection](#Prompt-Injection)
 - [Data Poisoning](#Data-Poisoning)
+
+<div align=center><img src="./img/four_attacks.png" width="60%" height="60%" /></div>
+
 ---
 
 ## Adversarial-Attack