PAIR uses an attacker LLM to iteratively craft effective jailbreak prompts for black-box target LLMs in fewer than 20 queries.
Catastrophic jail- break of open-source llms via exploiting generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.LG 1years
2023 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Jailbreaking Black Box Large Language Models in Twenty Queries
PAIR uses an attacker LLM to iteratively craft effective jailbreak prompts for black-box target LLMs in fewer than 20 queries.