AI Paper Atlas

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

Automatic Dialectic Jailbreak: A Framework for Generating Effective Jailbreak Strategies

Jianghai Yu, Yang Zhou, Zihan Zhou, Lingjuan Lyu, Da Yan, Ruoming Jin, Dejing Dou

ICLR 2026 · Large language models › Language, safety and interpretability · approach: Jailbreak attacks and defenses

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
use W-ADJ instead of best baselinejailbreak attack · AdvBench Harmful BehaviorHS: +31.71%Improved
use W-ADJ instead of best baselinejailbreak attack · AdvBench Harmful BehaviorASR: +13.9%Improved
use B-ADJ instead of best baselinejailbreak attack · AdvBench Harmful BehaviorHS: +23.14%Improved
use B-ADJ instead of best baselinejailbreak attack · AdvBench Harmful BehaviorASR: +10.29%Improved
apply ADJ under RAIN defenseW-ADJ · AdvBench Harmful Behavior (RAIN)ASR/HS drop: 0.66% ASR drop, 2% HS drop vs baseline 18.22% and 18.73%Improved
increase number of attack strategies beyond 15 (ablation)ADJ · AdvBenchASR and HS: 15No clear effect
add Hegelian dialectic (defender) to attacker-evaluator self-play (ablation)ADJ · AdvBenchASR and HSImproved
change system prompt design (ablation)ADJ · AdvBenchASR and HSNo clear effect
apply ADJ under perplexity defenseADJ · AdvBench Harmful Behavior (Perplexity)ASR and HSNo 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