Jailbreak Attempt Detection

Detects jailbreak attempts designed to bypass AI safety mechanisms. Detection covers a broad taxonomy of techniques: named jailbreak methods (DAN, STAN, DUDE, AIM, etc.), mode-switching prompts (developer, maintenance, debug, unrestricted, god mode), roleplay-based constraint removal, fictional/hypothetical framing of harmful requests, authority claims (developer, admin, Anthropic/OpenAI impersonation), emotional manipulation and urgency-based coercion, compliance demands and refusal suppression, dual-response formatting, encoding-wrapped jailbreaks, and anti-policy/filter bypass language. Patterns are anchored with word boundaries and context windows to minimize false positives on legitimate security discussions.

建議回應

參考資料