Skip to content

LLM jailbreak detection based on contrastive prototype structure

Jailbreak Detection on Large Language Models via Contrastive Prototype Structures

arXiv: Jailbreaks, Prompt Injection, Poisoning & Defenses· arXiv:2611.24936· Yan Qiu, Yuanyuan Li·Indexed by this site · 12 hr ago· Originally publishedDefenses· Its place in the scan record →
AI summary

Proposes an LLM jailbreak detection method, JDPI: it builds harmful and benign prototypes using only binary safety labels and predicts by relative distance to the prototypes, without training an additional downstream classifier. On four benchmarks, compared with fine-tuning, it improves detection accuracy by 9.1-18.0 percentage points, and after dataset adaptation its ROC-AUC exceeds the Llama Guard 3-8B baseline by 0.173-0.310. Across 12 targeted transfers, accuracy is on average 1.59 percentage points higher than the classifier.

Read originalarxiv.org