English(EN) Backdoor Purification for LoRA-Tuned LLMs via Null-Space Projection

新方法净化 LoRA 微调的 LLM 免受后门攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-02 04:00

研究人员开发了一种名为零空间投影的新方法，用于净化使用 LoRA（低秩适应）进行微调的大型语言模型（LLM）。该技术旨在降低后门攻击的成功率，而无需预先了解触发器、干净的参考或激进的再训练。该方法将 LoRA 更新投影到输入和输出通道的正交零空间上，显著降低了攻击成功率，同时保留了模型的通用能力和新获得的下游技能。 AI

影响为针对微调 LLM 的复杂后门攻击提供了一种新颖的防御手段，增强了模型的安全性和可信度。

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

在 arXiv cs.AI 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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 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.AI TIER_1 English(EN) · Jianwei Li, Jung-Eun Kim · 2026-10-02 04:00

通过零空间投影为 LoRA 微调的大模型进行后门净化

arXiv:2610.00685v1 Announce Type: new Abstract: With the rapid adoption of large language models (LLMs) and parameter-efficient fine-tuning (PEFT) methods, the risk of backdoor attacks has become more severe. Existing backdoor purification methods typically rely on at least one o…

本文如何被排名

报道来源 [1]

通过零空间投影为 LoRA 微调的大模型进行后门净化

相关实体

相关话题