AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SceneJailEval: A Scenario-Adaptive Multi-Dimensional Framework for Jailbreak Evaluation

Lai Jiang, Yuekang Li, Xiaohan Zhang, Youtao Ding, Li Pan

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 2 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
add scenario classification on top of dimension scoring (ablation)SceneJailEval · SceneJailEval datasetF1: 0.8903 -> 0.9169Improved
add scenario-adaptive dimension selection beyond vanilla heuristic rules (ablation)SceneJailEval · SceneJailEval datasetF1: 0.8314 -> 0.9169Improved
use SceneJailEval instead of best baseline judge (Qi2023)jailbreak evaluator · SceneJailEval datasetF1: 0.8508 -> 0.9148Improved
use SceneJailEval instead of Beaver (fine-tuned on Safe-RLHF)jailbreak evaluator · Safe-RLHFF1: 0.91 -> 0.83Hurt
use SceneJailEval instead of JailJudge baselinejailbreak evaluator · JailJudge datasetF1: 0.81 -> 0.82Improved
use SceneJailEval instead of llamaguard3jailbreak evaluator · JBBF1: 0.98 -> 0.99Improved

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