Skip to content
attack.paths
Sign in
← LibraryTechnique entry
AI-JAILBREAKDefense Evasion

LLM Jailbreak

DAN / Sudo / persona / multi-turn escalation prompts that disable the model's safety alignment, enabling forbidden output.

§ Where this technique fits

AI-JAILBREAK is catalogued under the Defense Evasion tactic of the offensive-security kill-chain. It appears in 0 approved dossiers in the registry, typically.