hiw3c 日报精选
arXiv cs.AI/CL/LG 网页快照

基于对比原型结构在大语言模型上的越狱检测

原文标题 · Jailbreak Detection on Large Language Models via Contrastive Prototype Structures

作者: 邱岩、李远远 | 越狱尝试与有害提示对大语言模型的安全部署仍是一项挑战。我们研究对比学习表示是否能够支持安全检测,而无需训练额外的下游分类器。我们提出“原型推理式越狱检测”(JDPI),该方法使用二元安全标签来构建有害与良性原型,并进行预

来源:arXiv cs.AI/CL/LG · arxiv.org

正文为英文,可一键机器翻译(仅首次需要等待)

Computer Science > Computation and Language

Title: Jailbreak Detection on Large Language Models via Contrastive Prototype Structures

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.

Submission history

Access Paper:

Additional Features

Current browse context:

References & Citations

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .