English(EN) TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual Modulation

新的TERM防御在无目标的情况下提高了LLM越狱的鲁棒性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

研究人员开发了一种名为TERM（Target-free Entropy-guided Residual Modulation，无目标熵引导残差调制）的新防御机制，以对抗大型语言模型的越狱攻击。这种推理时防御通过分析注意力熵偏差来适应各种提示，并将其与基线进行校准，以区分有害和良性请求。TERM然后调整模型的内部残差更新，而不依赖预定义的安全方向，在Llama、Qwen和Gemma等模型上展示了对越狱的鲁棒性提高，同时最大限度地减少了对敏感但安全的提示的过度拒绝。 AI

影响通过提供一种新颖的对抗性提示防御方法来增强LLM安全性，可能导致AI系统更可靠的部署。

排序理由这是一篇详细介绍LLM安全新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 34 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍LLM安全新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Yunkai Dang, Wanyu Zhang, Meiyi Zhu, Qi Fan, Tianyu Ding, Wenbin Li · 2026-11-11 05:00

TERM：通过熵引导残差调制实现无目标越狱防御

arXiv:2611.13577v1 Announce Type: cross Abstract: Large language models (LLMs) have shown strong capabilities across diverse applications, making both safety and utility essential for reliable deployment. Jailbreak attacks use diverse forms of adversarial prompting to bypass alig…

本文如何被排名

报道来源 [1]

TERM：通过熵引导残差调制实现无目标越狱防御

相关实体

相关话题