AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search

Rongzhe Wei, Peizhi Niu, Xinjie Shen, Tony Tu, Yifan Li, Ruihan Wu, Eli Chien, Pin-Yu Chen, Olgica Milenkovic, Pan Li

ICML 2026 · Large language models › Language, safety and interpretability · approach: Jailbreak attacks and defenses · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace static a-priori decomposition (Multi-Agent Jailbreak) with adaptive tree-structured CKA-Agentdecomposition-based jailbreak · HarmBench, four commercial target LLMsFull Success rate: Claude-Haiku-4.5: 0.786 -> 0.960Improved
use prompt-optimization attacks against strongly aligned Claude-Haiku-4.5 instead of weaker targetsPAIR · HarmBenchFull Success rate: 0.810 (Gemini-2.5-Flash) -> 0.032 (Claude-Haiku-4.5)Hurt
let CKA-Agent see the full conversation history (single-session CKA-Agent-Branch) instead of cross-session queries (ablation)CKA-Agent · HarmBench on GPT-oss-120BFull Success rate: 0.976 -> 0.786Hurt
let CKA-Agent see the full conversation history (single-session CKA-Agent-Branch) (ablation)CKA-Agent · HarmBench on Gemini-2.5-FlashFull Success rate: 0.968 -> 0.921No clear effect
interactive querying of the target model versus attacker's own knowledge (ablation)CKA-Agent · HarmBench on Gemini-2.5-Proprompts solved (count): CKA Only 26 vs Self Only 2Improved
apply Llama Guard or Circuit Breaker defenses against optimization-based attacks (ablation)AutoDAN, PAIR, PAP, TAP, ActorBreaker · HarmBench on Gemini-2.5-FlashFull Success rateImproved
apply input-level defenses (Llama Guard, rephrasing, perturbation) against decomposition-based attacks (ablation)CKA-Agent and Multi-Agent Jailbreak · HarmBench on Gemini-2.5-FlashFull Success rateNo clear effect
apply Circuit Breaker representation-level defense against CKA-Agent (ablation)CKA-Agent · HarmBench on Gemini-2.5-FlashFull Success rateImproved
apply mutation-based defenses (rephrasing, character perturbation) (ablation)jailbreak methods · HarmBench on Gemini-2.5-FlashFull Success rateNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy