Update index.html

index.html

@@ -92,9 +92,11 @@ Exploring Refusal Loss Landscapes </title>
 
 <p>
   From the above plot, we find that the loss landscape is more precipitous for malicious queries than for benign queries, which implies that 
-  the <strong>Refusal Loss</strong> tends to have a large gradient norm if the input represents a malicious query. This observation motivates our proposal of using 
-  the gradient norm of <strong>Refusal Loss</strong> to detect jailbreak attempts that pass the initial filtering of rejecting the input query when the function value is under 0.5 (this is a naive detector bacause the Refusal Loss can be regarded as the probability that the LLM won't reject the user query).
-  Below we present the definition of the <strong>Refusal Loss</strong> and the approximation of its function value and gradient, see more details about them and the landscape drawing techniques in our paper. 
+  the Refusal Loss tends to have a large gradient norm if the input represents a malicious query. This observation motivates our proposal of using 
+  the gradient norm of Refusal Loss to detect jailbreak attempts that pass the initial filtering of rejecting the input query when the function value 
+  is under 0.5 (this is a naive detector because the Refusal Loss can be regarded as the probability that the LLM won't reject the user query).
+  Below we present the definition of the Refusal Loss and the approximation of its function value and gradient, see more details about them and 
+  the landscape drawing techniques in our paper. 
 </p>
 
 <div id="refusal-loss-formula" class="container">
@@ -156,7 +158,7 @@ We provide more details about the running flow of Gradient Cuff in the paper.
       
 <h2 id="demonstration">Demonstration</h2>
 <p>We evaluated Gradient Cuff as well as 4 baselines (Perplexity Filter, SmoothLLM, Erase-and-Check, and Self-Reminder) 
-  against 6 different jailbreak attacks~(GCG, AutoDAN, PAIR, TAP, Base64, and LRL) and benign user queries on 2 LLMs (LLaMA-2-7B-Chat and 
+  against 6 different jailbreak attacks (GCG, AutoDAN, PAIR, TAP, Base64, and LRL) and benign user queries on 2 LLMs (LLaMA-2-7B-Chat and 
   Vicuna-7B-V1.5). We below demonstrate the average refusal rate across these 6 malicious user query datasets as the Average Malicious Refusal 
   Rate and the refusal rate on benign user queries as the Benign Refusal Rate. The defending performance against different jailbreak types is 
   shown in the provided bar chart.