INTACT: Compact Storage of Data Streams in Mobile Devices to Unlock User Privacy at the Edge

2025-06-27

AI Summary

To address the challenge of deploying privacy-preserving mechanisms—such as Location Privacy-Preserving Mechanisms (LPPMs)—on resource-constrained mobile devices, this paper proposes INTACT, a lightweight edge privacy-computing framework. INTACT employs piecewise linear interpolation (PLI) for compact streaming data compression and introduces a “Divide & Stay” localized privacy protection scheme that enables point-of-interest (POI) inference directly on-device, thereby eliminating the need to upload sensitive raw data. Notably, INTACT is the first framework to realize end-to-end, lightweight edge privacy computation on real-world Android and iOS platforms. Experimental evaluations demonstrate substantial reductions in on-device storage and network communication overhead, while rigorously satisfying formal privacy guarantees (e.g., differential privacy or its variants). By bridging the gap between theoretical privacy mechanisms and practical mobile deployment, INTACT provides a deployable, production-ready solution for privacy-preserving mobile computing.

Technology Category

• Machine Learning: Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Computer Vision: Bias, Fairness & Privacy

Application Category

• Security and Privacy: Privacy-enhancing technologies
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Data streams produced by mobile devices, such as smartphones, offer highly valuable sources of information to build ubiquitous services. Such data streams are generally uploaded and centralized to be processed by third parties, potentially exposing sensitive personal information. In this context, existing protection mechanisms, such as Location Privacy Protection Mechanisms (LPPMs), have been investigated. Alas, none of them have actually been implemented, nor deployed in real-life, in mobile devices to enforce user privacy at the edge. Moreover, the diversity of embedded sensors and the resulting data deluge makes it impractical to provision such services directly on mobiles, due to their constrained storage capacity, communication bandwidth and processing power. This article reports on the FLI technique, which leverages a piece-wise linear approximation technique to capture compact representations of data streams in mobile devices. Beyond the FLI storage layer, we introduce Divide & Stay, a new privacy preservation technique to execute Points of Interest (POIs) inference. Finally, we deploy both of them on Android and iOS as the INTACT framework, making a concrete step towards enforcing privacy and trust in ubiquitous computing systems.

Problem

• Protect sensitive personal data in mobile streams
• Overcome mobile storage and processing constraints
• Enable privacy-preserving edge computing for ubiquitous services

Innovation

• FLI technique for compact data stream storage
• Divide & Stay for privacy preservation
• INTACT framework deployment on Android and iOS