Commit
·
cf4928f
1
Parent(s):
17fc37d
Update README.md
Browse files
README.md
CHANGED
@@ -26,7 +26,7 @@ Experimental results on several safety benchmark datasets indicate that **Starli
|
|
26 |
|
27 |
**This jailbreak prompt (termed as Chain of Utterances (CoU) prompt in the paper) shows a 65% Attack Success Rate (ASR) on GPT-4 and 72% on ChatGPT.**
|
28 |
|
29 |
-
<img src="https://declare-lab.net/assets/images/logos/
|
30 |
|
31 |
<h2>HarmfulQA Data Collection</h2>
|
32 |
|
|
|
26 |
|
27 |
**This jailbreak prompt (termed as Chain of Utterances (CoU) prompt in the paper) shows a 65% Attack Success Rate (ASR) on GPT-4 and 72% on ChatGPT.**
|
28 |
|
29 |
+
<img src="https://declare-lab.net/assets/images/logos/jailbreakprompt_main_paper.png" alt="Image" width="1000" height="1000">
|
30 |
|
31 |
<h2>HarmfulQA Data Collection</h2>
|
32 |
|