新型后门攻击方法仅需一个中毒数据样本

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-28 04:00

研究人员开发了一种针对机器学习模型的新型后门攻击方法，特别针对线性模型和ReLU神经网络。这种被称为“一次中毒后门攻击”的技术仅需一个恶意数据样本，且无需了解单个训练数据点。该攻击可以使用输入空间和训练参数的粗略几何边界来执行，在不显著影响模型良性性能的情况下实现零后门错误。 AI

影响这项研究突显了机器学习模型的一个重大漏洞，可能影响在不受信任数据上训练的AI系统的安全性和可信度。

排序理由详细介绍一种新型机器学习攻击方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

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: 24 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍一种新型机器学习攻击方法的学术论文。[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。

arXiv cs.LG TIER_1 English(EN) · Thorsten Peinemann, Paula Arnold, Sebastian Berndt, Thomas Eisenbarth, Esfandiar Mohammadi · 2026-08-28 04:00

Provable one-poison backdoor attacks on linear models and ReLU neural networks

arXiv:2508.05600v3 Announce Type: replace Abstract: Backdoor poisoning attacks are a threat to machine learning models that are trained on data collected from untrusted sources; these attacks enable attackers to inject malicious behavior into the model that can be triggered by sp…