AGILE is a two-stage jailbreak attack that combines scenario-based rephrasing with activation-guided local editing to reach state-of-the-art attack success rates and strong black-box transferability.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Activation-Guided Local Editing for Jailbreaking Attacks
AGILE is a two-stage jailbreak attack that combines scenario-based rephrasing with activation-guided local editing to reach state-of-the-art attack success rates and strong black-box transferability.