change the body style

index.html

@@ -76,12 +76,12 @@
     <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
 <!-- end custom head snippets -->
     <style>
-      body {
+      /* body {
           font-family: Arial, sans-serif;
           text-align: center;
           background-color: #f4f4f4;
-          padding: 20px;
-      }
+          padding: 0px;
+      } */
 
       .image-gallery {
           display: flex; /* Use flexbox for side-by-side images */
@@ -92,7 +92,7 @@
 
       .image-gallery img {
           width: 100%; /* Set width to 80% of the window */
-          max-width: 800px; /* Ensure maximum width remains 500px */
+          max-width: 1200px; /* Ensure maximum width remains 500px */
           height: auto; /* Maintain aspect ratio */
           border-radius: 10px; /* Rounded corners for images */
           box-shadow: 0 4px 10px rgba(0, 0, 0, 0.1); /* Add shadow to images */
@@ -253,7 +253,7 @@ We provide more details about the running flow of Attention Tracker in the paper
 <h2 id="demonstration">Demonstration</h2>
 
 <p>
-  We evaluated the effectiveness of the Attention Tracker by visualizing the distribution of attention aggregation for key heads across different data types (normal data vs. attack data) in the Open-Prompt-Injection dataset. Additionally, we calculated the focus score for these data samples. A higher focus score indicates a lower likelihood of prompt injection attacks.
+  We evaluated the effectiveness of the Attention Tracker by visualizing the distribution of attention aggregation for key heads across different data types (normal data vs. attack data) in the Open-Prompt-Injection dataset. Additionally, we calculated the focus score for these data samples. A higher focus score indicates a lower likelihood of prompt injection attacks. The tested model is Qwen-2 1.8b.
 </p>
 
 <div class="button-container">