Update index.html
Browse files- index.html +3 -1
index.html
CHANGED
|
@@ -143,7 +143,9 @@ Exploring Refusal Loss Landscapes </title>
|
|
| 143 |
<ul>
|
| 144 |
<li>Paper: <a href="https://arxiv.org/abs/2312.02119" target="_blank" rel="noopener noreferrer">
|
| 145 |
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically</a></li>
|
| 146 |
-
<li>Brief Introduction:
|
|
|
|
|
|
|
| 147 |
</ul>
|
| 148 |
</div>
|
| 149 |
<h3>Base64</h3>
|
|
|
|
| 143 |
<ul>
|
| 144 |
<li>Paper: <a href="https://arxiv.org/abs/2312.02119" target="_blank" rel="noopener noreferrer">
|
| 145 |
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically</a></li>
|
| 146 |
+
<li>Brief Introduction: TAP is similar to PAIR. The main difference is that
|
| 147 |
+
the attacker in TAP iteratively refines candidate (attack) prompts using tree-of-thought
|
| 148 |
+
reasoning.</li>
|
| 149 |
</ul>
|
| 150 |
</div>
|
| 151 |
<h3>Base64</h3>
|