cs.CLNov 18, 2026

Jailbreak Detection on Large Language Models via Contrastive Prototype Structures

Authors: Yan Qiu, Yuanyuan Li

Organizations: Department of Mathematics, Technical University of Munich, Garching, Germany · Insure AI, Munich Re, San Francisco, USA

Abstract

Jailbreak attempts and harmful prompts remain a challenge for the safe deployment of large language models. We study whether contrastively learned representations can support safety detection without training an additional downstream classifier. We propose Jailbreak Detection with Prototype Inference (JDPI), which uses binary safety labels to construct harmful and benign prototypes and makes predictions from relative prototype distances. JDPI uses only binary safety labels for encoder adaptation, prototype construction, and validation. In our setup, it uses fewer labeled examples than the classifier baseline (Method A) by avoiding the separate split used to train the downstream classifier. Across four benchmarks covering different input formats, contrastive fine-tuning improves JDPI's detection accuracy by 9.1-18.0 percentage points. Using the same encoder, JDPI achieves slightly higher ROC-AUC on one benchmark and stays within 0.017 of the baseline across all four. With dataset-specific adaptation, JDPI exceeds the released Llama Guard 3-8B baseline by 0.173-0.310 in ROC-AUC across the four benchmarks. In multi-turn replay on TomGibbs, JDPI uses accumulated user history as the conversation unfolds, achieving higher conversation-level accuracy than when it uses the current turn alone. Across 12 directed transfers, JDPI outperforms the classifier by an average of 1.59 percentage points in accuracy, demonstrating stronger cross-dataset robustness.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models

    Sep 16, 2026Alizishaan Khatri, Chiquita Prabhu, Omkar NeogiSafety FilteringLLM Safety

  2. SafeDream: Safety World Model for Proactive Early Jailbreak Detection

    Apr 18, 2026Bo Yan, Weikai Lin, Yada Zhu +1Language Model Safety EvaluationWorld Models