paper-with-me

홈 › Papers

Local Is Not a Sufficient Privacy Boundary: Governing OS-Integrated On-Device AI

2026-06-08 · Jonghyun Chung, Sanket Badhe arxiv

As AI systems move into operating systems, privacy no longer turns only on whether a model runs locally. A local assistant may assemble email, calendar entries, files, screenshots, notifications, and app intents; retain embeddings or summaries; invoke tools; emit telemetry; or route difficult requests to cloud infrastructure. Local inference reduces some exposure, but it answers only one question: where computation occurs. It does not answer who may assemble context, what derived state persists, which actions are authorized, or how updates change the system's authority. We develop an OS-centered privacy framework for on-device AI that treats privacy as an institutional accountability problem rather than a deployment attribute. The framework specifies a threat model, a six-part privacy risk taxonomy, privacy-by-architecture controls, and a four-level audit rubric. We demonstrate the rubric through a documentation-bounded comparison of Apple Intelligence/Foundation Models, Android AICore/Gemini Nano, and Microsoft Recall. Meaningful privacy in on-device AI depends on constrained information flow, bounded authority, visible user control, and auditable governance across the operating-system lifecycle.

📄 PDF Abstract BibTeX arXiv:2606.10173

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Active Membership Inference Attack under Local Differential Privacy in Federated Learning

2023-02-24 · Truc Nguyen, Phung Lai, Khang Tran, NhatHai Phan 외

Federated learning (FL) was originally regarded as a framework for collaborative learning among clients with data privacy protection through a coordinating server. In this paper, we propose a new active membership infere…

Federated LearningInference AttackMembership Inference AttackPrivacy Preserving

An Enhanced Privacy-preserving Federated Few-shot Learning Framework for Respiratory Disease Diagnosis

2025-07-10 · Ming Wang, Zhaoyang Duan, Dong Xue, Fangzhou Liu 외

The labor-intensive nature of medical data annotation presents a significant challenge for respiratory disease diagnosis, resulting in a scarcity of high-quality labeled datasets in resource-constrained settings. Moreove…

DiagnosticFew-Shot LearningPrivacy Preserving

Joint discovery of governing partial differential equations from multi-source datasets by competitive optimization

2026-06-29 · Hao Xu, Siyu Lou, Yuntian Chen, Dongxiao Zhang arxiv

Discovering governing equations directly from observational data is a key step towards interpretable scientific machine learning. Current data-driven approaches typically operate on a single dataset, inherently limiting …

LSA-PINN: Linear Boundary Connectivity Loss for Solving PDEs on Complex Geometry

2023-02-03 · Jian Cheng Wong, Pao-Hsiung Chiu, Chinchun Ooi, My Ha Dao 외

We present a novel loss formulation for efficient learning of complex dynamics from governing physics, typically described by partial differential equations (PDEs), using physics-informed neural networks (PINNs). In our …

Differential equations of electrodiffusion: constant field solutions, uniqueness, and new formulas of Goldman-Hodgkin-Katz type

2016-09-21

The equations governing one-dimensional, steady-state electrodiffusion are considered when there are arbitrarily many mobile ionic species present, in any number of valence classes, possibly also with a uniform distribut…