The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
Researchers developed a method called CKA-Agent to bypass LLM safety guardrails by weaving together many seemingly harmless questions. The agent uses an adaptive tree search strategy, asking benign sub-queries that exploit the model's interconnected knowledge. This approach succeeds by letting the model reconstruct harmful information through a sequence of safe interactions, showing current defenses fail against distributed intent.