AI Paper Atlas

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

CHASE: Contextual History for Adaptive and Simple Exploitation in Large Language Model Jailbreaking

Zhiqiang Hao, Chuanyi Li, Ye Fan, Jun Cai, Xiao Fu, Shangqi Wang, Hao Shen, Jiao Yin, Jidong Ge, Bin Luo, Vincent Ng

AAAI 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
transfer jailbroken histories from an easy-to-jailbreak LLM to the target and prompt continuation (CHASE) instead of best baseline attackstarget LLMs · AdvBench jailbreakASR (%): 89.2 -> 95.8 (GPT-4, DRA vs CHASE)Improved
CHASE versus DRA on Llama3-70bLlama3-70b · AdvBench jailbreakASR (%): 85.2 -> 85.8No clear effect
CHASE requires 2-3 queries versus CodeAttack 20.80-30.31attack efficiency · AdvBench efficiencyaverage queries: 20.80 -> 2.12 (GPT-3.5)Improved
CHASE versus LLM-Fuzzer on preparation costattack efficiency · AdvBench efficiencyQBC: 285.6 -> 8.5Improved
replace CHASE history generation with DRA to produce histories (ablation)CHASE · AdvBench jailbreakASR (%): 98.3 -> 21.7 (GPT-3.5)Hurt
replace CHASE history generation with CFA (ablation)CHASE · AdvBench jailbreakASR (%): 98.3 -> 61.3 (GPT-3.5)Hurt
increase number of history-generation turns from one to four (ablation)history generation on Qwen1.5-72B · AdvBench history generationASR (%): 72.1 -> 100.0Improved
add LlamaGuard3-8B prompt filter defense (ablation)CHASE · AdvBench jailbreakASR (%): 98.3 -> 78.8 (GPT-3.5)Hurt
add refusal reminder to user prompt as defense (ablation)CHASE · AdvBench jailbreakASR (%): 98.3 -> 15.4 (GPT-3.5)Hurt
add refusal defenses (Guard, UsrPrompt, SysPrompt) to the target modeltarget LLMs · AlpacaEvalwin rate (%): 51.3 -> 45.0 (GPT-4o, Guard)Hurt

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