AI Security

New Preprint: CKA-Agent Achieves 96-99% Jailbreak Success on GPT, Gemini & Claude
Our new paper introduces CKA-Agent, a novel framework that bypasses commercial LLM guardrails through adaptive tree search over correlated knowledge.
Xinjie Shen 沈鑫杰
Last updated on Sep 27, 2026 1 min read Research
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
Introduce CKA-Agent, a framework that reformulates jailbreaking as an adaptive tree search over the target LLM’s correlated knowledge, achieving 96-99% attack success rates against state-of-the-art commercial LLMs.
Rongzhe Wei, Peizhi Niu, Xinjie Shen 沈鑫杰, Tong Tu, Yifan Li, Ruihan Wu, Eli Chien, Pin-Yu Chen, Olgica Milenkovic, Pan Li
PDF Project Page
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search