JADES judges jailbreak success by decomposing harmful prompts into weighted sub-questions and scoring each part, claiming 98.5% human agreement and showing prior attack success rates are inflated.
Generated data with fake privacy: Hidden dangers of fine- tuning large language models on generated data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring
JADES judges jailbreak success by decomposing harmful prompts into weighted sub-questions and scoring each part, claiming 98.5% human agreement and showing prior attack success rates are inflated.