Update index.html

index.html

@@ -223,7 +223,7 @@ Exploring Refusal Loss Landscapes </title>
   
 </div>
 
-<h2 id="refusal-loss">Refusal Loss Landscape Exploration</h2>
+<h2 id="refusal-loss">Interpretability</h2>
 <p>Current transformer-based LLMs will return different responses to the same query due to the randomness of 
   autoregressive sampling-based generation. With this randomness, it is an 
   interesting phenomenon that a malicious user query will sometimes be rejected by the target LLM, but 
@@ -286,7 +286,7 @@ Exploring Refusal Loss Landscapes </title>
 </div>
 </div>
 
-<h2 id="proposed-approach-gradient-cuff">Proposed Approach: Gradient Cuff</h2>
+<h2 id="proposed-approach-gradient-cuff">Experimental results on benchmarks</h2>
 <p> With the exploration of the Refusal Loss landscape, we propose Gradient Cuff, 
   a two-step jailbreak detection method based on checking the refusal loss and its gradient norm. Our detection procedure is shown below:
 </p>