equation

index.html

@@ -39,7 +39,7 @@
         e.preventDefault();
         if (!$(this).hasClass('selected')) {
 
-            $('.formula').hide(200);
+            $('.adaptive-loss-formula-content > .formula').hide(200);
             $('.formula-list > a').removeClass('selected');
             $(this).addClass('selected');
             var target = $(this).attr('href');
@@ -420,8 +420,8 @@
       <div class="column container formula">
         <p>
           Attackers can design adaptive attacks to try to bypass BEYOND when the attacker knows all the parameters of the model 
-          and the detection strategy. For an SSL model with a feature extractor <equation-inline>f</equation-inline>, a projector $h$, and a classification head $g$, 
-          the classification branch can be formulated as <equation-inline>\mathbb{C} = f\circ g</equation-inline> and the representation branch as $\mathbb{R} = f\circ h$. 
+          and the detection strategy. For an SSL model with a feature extractor $$f$$, a projector $h$, and a classification head $g$, 
+          the classification branch can be formulated as $$\mathbb{C} = f\circ g$$ and the representation branch as $$\mathbb{R} = f\circ h$$. 
           To attack effectively, the adversary must deceive the target model while guaranteeing the label consistency and representation similarity of the SSL model. 
       </div>
     </div>
@@ -435,7 +435,7 @@
             <a href=".total-loss">Total Loss</a>
             <div style="clear: both"></div>
           </div>
-          <div id="adaptive-loss-formula-content" class="row align-items-center">
+          <div class="row align-items-center adaptive-loss-formula-content>
             <span class="formula label-loss" style="">
               $$
               \displaystyle 
@@ -457,16 +457,16 @@
     </div>
 
     <div class="columns is-centered">
-      <div class="column container">
+      <div class="column container adaptive-loss-formula-content">
         <p class="formula label-loss">
-          where $\displaystyle k$ represents the number of generated neighbors, $\displaystyle y_t$ is the target class, and $\displaystyle \mathcal{L}$ is the cross entropy loss function
+          where $$k$$ represents the number of generated neighbors, $$y_t$$ is the target class, and $$\mathcal{L}$$ is the cross entropy loss function.
         </p>
         <p class="formula representation-loss" style="display: none">
-          where $\displaystyle \mathcal{S}$ is the cosine similarity.
+          where $$\mathcal{S}$$ is the cosine similarity.
         </p>
           
         <p class="formula total-loss" style="display: none;">
-          where $\displaystyle \mathcal{L}_C$ indicates classifier's loss function, $\displaystyle y_t$ is the targeted class, and $\displaystyle \alpha$ refers to a hyperparameter.
+          where $$\mathcal{L}_C$$ indicates classifier's loss function, $y_t$ is the targeted class, and $\alpha$ refers to a hyperparameter.
         </p>
       </div>
     </div>