CKA-Agent
Input and output guardrails
[ICML 2026 & ICLR 2026 AIWILD] Official Implementation of the CKA-Agent, "The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search".
Contribute
Spot an error, or know a record we should add? Members can propose additions and submit corrections.