Towards Context-aware Mobile Privacy Notice: Implementation of A Deployable Contextual Privacy Policies Generator

2025-09-26

AI Summary

Mobile app privacy policies are often lengthy and unintelligible, hindering users’ understanding of data collection practices. Existing contextualized privacy policies (CPPs) face significant challenges in real-world mobile deployment. To address this, we propose PrivScan—the first practically deployable Android SDK for contextual privacy policies. Our approach employs a lightweight floating-button UI component coupled with a remote, decoupled multimodal backend that dynamically identifies GUI elements via real-time screenshot analysis and generates concise, scenario-aware privacy notices. The modular architecture ensures low on-device computational overhead while supporting cross-platform extensibility. Evaluation on real Android devices demonstrates an average response latency of only 9.15 seconds, confirming practical feasibility and efficiency. The implementation is open-sourced, accompanied by a demonstration video, providing a reproducible and deployable solution for enhancing privacy transparency on mobile platforms.

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
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Lengthy and legally phrased privacy policies impede users' understanding of how mobile applications collect and process personal data. Prior work proposed Contextual Privacy Policies (CPPs) for mobile apps to display shorter policy snippets only in the corresponding user interface contexts, but the pipeline could not be deployable in real-world mobile environments. In this paper, we present PrivScan, the first deployable CPP Software Development Kit (SDK) for Android. It captures live app screenshots to identify GUI elements associated with types of personal data and displays CPPs in a concise, user-facing format. We provide a lightweight floating button that offers low-friction, on-demand control. The architecture leverages remote deployment to decouple the multimodal backend pipeline from a mobile client comprising five modular components, thereby reducing on-device resource demands and easing cross-platform portability. A feasibility-oriented evaluation shows an average execution time of 9.15,s, demonstrating the practicality of our approach. The source code of PrivScan is available at https://github.com/buyanghc/PrivScan and the demo video can be found at https://www.youtube.com/watch?v=ck-25otfyHc.

Problem

• Generating contextual privacy policies for mobile applications
• Implementing deployable privacy notice system for Android
• Reducing resource demands for cross-platform privacy solutions

Innovation

• Deployable SDK generates contextual privacy policies for Android
• Captures screenshots to identify GUI elements with personal data
• Uses remote deployment for lightweight cross-platform portability