arXiv：cs.AI· Jonghyun Chung, Sanket Badhe·· 5 小时前
面向操作系统集成 AI 的特征边界审计方法：覆盖 Apple Foundation Models、Android AICore/Gemini Nano 与 Microsoft Recall
Beyond Locality: Feature-Boundary Auditing for OS-Integrated AI
AI 导读
研究者提出一种面向 OS 集成 AI 的特征边界审计方法，由六类隐私失效面分类、五维控制评估量表及相邻数据与权限路径记录组成，并已应用于 Apple Foundation Models、Apple Private Cloud Compute、Android AICore/Gemini Nano 和 Microsoft Recall 的公开文档分析。
正文
Abstract:On-device inference reduces exposure to remote infrastructure, but it does not establish privacy for an operating-system assistant that aggregates cross-application data, retains derived state, or delegates actions. We present a feature-boundary audit method for OS-integrated AI. It combines a taxonomy of six privacy-failure surfaces, a five-dimension control rubric with separate evidence grades, and explicit records for adjacent data and authority paths. We apply the method to Apple Foundation Models, Apple Private Cloud Compute, Android AICore/Gemini Nano, and Microsoft Recall using primary public documentation. The analysis distinguishes request isolation from contextual restraint, retained-state controls from non-retention, and attestation from task-appropriate disclosure. A formative comparison of two 20-item assessment records identifies ambiguities in notice, retention, path ownership, and accountability. The source-linked records identify supported controls and unresolved dependencies; we also specify a minimized event record and release comparison for fleet security triage and scoped forensic review.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.10173 [cs.CR] |
| (or arXiv:2606.10173v2 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2606.10173 arXiv-issued DOI via DataCite |
Submission history
From: Jonghyun Chung [view email]
[v1]
Mon, 8 Jun 2026 21:07:11 UTC (27 KB)
[v2]
Mon, 12 Oct 2026 01:31:00 UTC (27 KB)
来源：arXiv：cs.AI · arxiv.org