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") |
|||
| (2 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
== Attack methods == | == Attack and defense methods == | ||
{| class="wikitable" | {| class="wikitable" | ||
|+ | |+ | ||
!Name | !Name | ||
!Type | |||
!Description | !Description | ||
!Paper | !Paper | ||
|- | |- | ||
|GPT Fuzzer | |GPT Fuzzer | ||
|Attack | |||
|Repeatedly mutate attacks to retain effective ones. Outperforms existing methods. | |||
|2309.10253v2 | |||
|- | |||
| | |||
| | |||
| | |||
| | |||
|- | |||
| | |||
| | |||
| | | | ||
| | | | ||
|} | |||
== Datasets == | |||
{| class="wikitable" | |||
|+ | |||
!Name | |||
!Type | |||
!Description | |||
!Paper | |||
|- | |||
|TensorTrust | |||
|Prompt extraction/hijacking | |||
Attack and defense | |||
|Gathered from a game. | |||
|2311.01011v1 | |||
|- | |- | ||
| | |||
| | | | ||
| | | | ||
| | | | ||
|- | |- | ||
| | |||
| | | | ||
| | | | ||
Latest revision as of 22:55, 21 June 2024
Attack and defense methods
| Name | Type | Description | Paper |
|---|---|---|---|
| GPT Fuzzer | Attack | Repeatedly mutate attacks to retain effective ones. Outperforms existing methods. | 2309.10253v2 |
Datasets
| Name | Type | Description | Paper |
|---|---|---|---|
| TensorTrust | Prompt extraction/hijacking
Attack and defense |
Gathered from a game. | 2311.01011v1 |
