PasswordEval shows frontier models frequently leak passwords or confidential information, jailbreaks worsen failures, and reasoning traces leak secrets even when final answers do not.
Prompt leakage effect and mitigation strategies for multi-turn LLM ap- plications
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating Language Model Reasoning about Confidential Information
PasswordEval shows frontier models frequently leak passwords or confidential information, jailbreaks worsen failures, and reasoning traces leak secrets even when final answers do not.