allenhzy commited on
Commit
389972a
·
1 Parent(s): 81ae1a7
Files changed (1) hide show
  1. index.html +2 -2
index.html CHANGED
@@ -418,7 +418,7 @@
418
  <h2 class="title is-3">Adaptive Attack</h2>
419
 
420
  <div class="columns is-centered">
421
- <div class="column">
422
  <p>
423
  Attackers can design adaptive attacks to try to bypass BEYOND when the attacker knows all the parameters of the model
424
  and the detection strategy. For an SSL model with a feature extractor $\displaystyle f$, a projector $\displaystyle h$, and a classification head $\displaystyle g$,
@@ -458,7 +458,7 @@
458
  </div>
459
 
460
  <div class="columns is-centered">
461
- <div class="column">
462
  <p class="eq-des label-loss">
463
  where $\displaystyle k$ represents the number of generated neighbors, $\displaystyle y_t$ is the target class, and $\displaystyle \mathcal{L} is the cross entropy loss function$
464
  </p>
 
418
  <h2 class="title is-3">Adaptive Attack</h2>
419
 
420
  <div class="columns is-centered">
421
+ <div class="column container">
422
  <p>
423
  Attackers can design adaptive attacks to try to bypass BEYOND when the attacker knows all the parameters of the model
424
  and the detection strategy. For an SSL model with a feature extractor $\displaystyle f$, a projector $\displaystyle h$, and a classification head $\displaystyle g$,
 
458
  </div>
459
 
460
  <div class="columns is-centered">
461
+ <div class="column container">
462
  <p class="eq-des label-loss">
463
  where $\displaystyle k$ represents the number of generated neighbors, $\displaystyle y_t$ is the target class, and $\displaystyle \mathcal{L} is the cross entropy loss function$
464
  </p>