English(EN) Implementing a White-Box Undetectable Backdoor for Random Fourier Features

使用标准工具实现的RFF模型的白盒后门攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-16 04:00

研究人员已经实现了对使用随机傅里叶特征（RFF）的机器学习模型的理论白盒后门攻击。此实现使用NumPy和SciPy等标准科学计算工具构建，测试了此类攻击的实际可行性，这些攻击即使在拥有模型权重完全访问权限的情况下也旨在不可检测。研究发现，在各种稀疏度比率下，后门模型和干净模型之间没有可检测的差异，这有助于理解这些复杂的加密威胁的可实现性。 AI

影响证明了机器学习模型中不可检测后门的实际可行性，引发了对模型安全和审计的担忧。

排序理由学术论文，详细介绍了一种理论安全漏洞的新实现。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 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: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一种理论安全漏洞的新实现。[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.LG TIER_1 English(EN) · Michael Collins, Jada Cumberland, Brianne Dunn, Ross Gore, Samuel Jackson, Sachin Shetty · 2026-09-16 04:00

为随机傅里叶特征实现一种白盒不可检测后门

arXiv:2609.16403v1 Announce Type: cross Abstract: Goldwasser et al. showed that undetectable backdoors can be planted in machine learning models trained with the Random Fourier Features (RFF) algorithm, under a hardness assumption tied to the Continuous Learning With Errors (CLWE…

本文如何被排名

报道来源 [1]

为随机傅里叶特征实现一种白盒不可检测后门

相关实体

相关话题