gregH commited on
Commit
14275e6
1 Parent(s): 2f76d7a

Update index.html

Browse files
Files changed (1) hide show
  1. index.html +2 -1
index.html CHANGED
@@ -112,7 +112,8 @@ Exploring Refusal Loss Landscapes </title>
112
  <ul>
113
  <li>Paper: <a href="https://arxiv.org/abs/2307.15043" target="_blank" rel="noopener noreferrer">
114
  Universal and Transferable Adversarial Attacks on Aligned Language Models</a></li>
115
- <li>Brief Introduction: </li>
 
116
  </ul>
117
  </div>
118
  <h3>AutoDAN</h3>
 
112
  <ul>
113
  <li>Paper: <a href="https://arxiv.org/abs/2307.15043" target="_blank" rel="noopener noreferrer">
114
  Universal and Transferable Adversarial Attacks on Aligned Language Models</a></li>
115
+ <li>Brief Introduction: Given a (potentially harmful) user query, GCG trains and appends an adversarial suffix to the query
116
+ that attempts to induce negative behavior from the target LLM. </li>
117
  </ul>
118
  </div>
119
  <h3>AutoDAN</h3>