diff --git a/README.md b/README.md
index 1077887..225d4aa 100644
--- a/README.md
+++ b/README.md
@@ -27,7 +27,7 @@ Here, we've summarized existing LVLM Attack methods in our survey paper👍.
 - [Prompt Injection](#Prompt-Injection)
 - [Data Poisoning](#Data-Poisoning)
 
-<div align=center><img src="./img/four_attacks.png" width="60%" height="60%" /></div>
+<div align=center><img src="./img/four_attacks.png" width="80%" height="80%" /></div>
 
 ---