Prompt attack and defense: Difference between revisions

From Rice Wiki
(Created page with "== Attack methods == {| class="wikitable" |+ !Name !Description !Paper |- |GPT Fuzzer | | |- | | | |- | | | |} Category:Cybersecurity Category:LLM")
 
Line 7: Line 7:
|-
|-
|GPT Fuzzer
|GPT Fuzzer
|
|Repeatedly mutate attacks to retain effective ones. Outperforms existing methods.
|
|2309.10253v2
|-
|-
|
|

Revision as of 22:32, 21 June 2024

Attack methods

Name Description Paper
GPT Fuzzer Repeatedly mutate attacks to retain effective ones. Outperforms existing methods. 2309.10253v2