Update index.html

index.html

@@ -4,13 +4,13 @@
     <meta charset="UTF-8">
 
 <!-- Begin Jekyll SEO tag v2.8.0 -->
-<title>Gradient Cuff | Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes </title>
-<meta property="og:title" content="Gradient Cuff" />
+<title>NCTV | Neural Clamping Toolkit and Visualization for Neural Network Calibration</title>
+<meta property="og:title" content="NCTV" />
 <meta property="og:locale" content="en_US" />
-<meta name="description" content="Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes" />
-<meta property="og:description" content="Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes" />
+<meta name="description" content="Neural Clamping Toolkit and Visualization for Neural Network Calibration" />
+<meta property="og:description" content="Neural Clamping Toolkit and Visualization for Neural Network Calibration" />
 <script type="application/ld+json">
-{"@context":"https://schema.org","@type":"WebSite","description":"Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes","headline":"Gradient Cuff","name":"Gradient Cuff","url":"https://huggingface.co/spaces/gregH/NCTV-GradientCuff"}</script>
+{"@context":"https://schema.org","@type":"WebSite","description":"Neural Clamping Toolkit and Visualization for Neural Network Calibration","headline":"NCTV","name":"NCTV","url":"https://huggingface.co/spaces/hsiung/NCTV"}</script>
 <!-- End Jekyll SEO tag -->
 
     <link rel="preconnect" href="https://fonts.gstatic.com">
@@ -45,8 +45,8 @@
     <a id="skip-to-content" href="#content">Skip to the content.</a>
 
     <header class="page-header" role="banner">
-      <h1 class="project-name">Gradient Cuff</h1>
-      <h2 class="project-tagline">Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes</h2>
+      <h1 class="project-name">NCTV</h1>
+      <h2 class="project-tagline">Neural Clamping Toolkit and Visualization for Neural Network Calibration</h2>
       
       
     </header>
@@ -62,7 +62,7 @@ our proposed framework <strong>Neural Clamping</strong>, which employs a simple
 transformation on a pre-trained classifier. We also provide other calibration approaches
 (e.g., temperature scaling) to compare with Neural Clamping.</p>
 
-<h2 id="what-is-jailbreak">What is Jailbreak?</h2>
+<h2 id="what-is-calibration">What is Calibration?</h2>
 <p>Neural Network Calibration seeks to make model prediction align with its true correctness likelihood.
 A well-calibrated model should provide accurate predictions and reliable confidence when making inferences. On the
 contrary, a poor calibration model would have a wide gap between its accuracy and average confidence level.
@@ -70,24 +70,24 @@ This phenomenon could hamper scenarios requiring accurate uncertainty estimation
 (e.g., autonomous driving systems, medical diagnosis, etc.).</p>
 
 <div class="container">
-<div id="jailbrerak-intro" class="row align-items-center jailbreak-intro-sec">
-<img id="jailbreak-intro-img" src="https://hsiung.cc/NCTV/images/conf_acc_demo.gif" />
+<div id="calibration-intro" class="row align-items-center calibration-intro-sec">
+<img id="calibration-intro-img" src="https://hsiung.cc/NCTV/images/conf_acc_demo.gif" />
 </div>
 </div>
 
-<h3 id="refusal-loss-function">Refusal Loss Function</h3>
+<h3 id="calibration-metrics">Calibration Metrics</h3>
 <p>Objectively, researchers utilize <strong>Calibration Metrics</strong> to measure the calibration error for a model, for example,
 Expected Calibration Error (ECE), Static Calibration Error (SCE), Adaptive Calibration Error (ACE), etc.</p>
 
-<div class="container refusal-loss-function-intro-sec">
-<div><img id="refusal-loss-function-intro-img" src="images/metrics/intro-metric-example.png" /></div>
+<div class="container calibration-intro-sec">
+<div><img id="calibration-intro-img" src="images/metrics/intro-metric-example.png" /></div>
 </div>
 
-<div id="refusal-loss-formula" class="container">
-<div id="refusal-loss-formula-list" class="row align-items-center formula-list">
-  <a href="#ECE-formula" class="selected">RL</a>
-  <a href="#SCE-formula">SRR</a>
-  <a href="#ACE-formula">GE</a>
+<div id="calibration-metrics-formula" class="container">
+<div id="calibration-metrics-formula-list" class="row align-items-center formula-list">
+  <a href="#ECE-formula" class="selected">ECE</a>
+  <a href="#SCE-formula">SCE</a>
+  <a href="#ACE-formula">ACE</a>
   <div style="clear: both"></div>
 </div>
 <div id="calibration-metrics-formula-content" class="row align-items-center">