Quantifying the Privacy-Utility Trade-off in GPS-based Daily Stress Recognition using Semantic Features

2025/11/28 by Phan, Hoang Khang, Le, Nhat Tan
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)

paper · doi:10.48550/arxiv.2511.23200

Abstract

Psychological stress is a widespread issue that significantly impacts student well-being and academic performance. Effective remote stress recognition is crucial, yet existing methods often rely on wearable devices or GPS-based clustering techniques that pose privacy risks. In this study, we introduce a novel, end-to-end privacy-enhanced framework for semantic location encoding using a self-hosted OSM engine and an LLM-bootstrapped static map. We rigorously quantify the privacy-utility trade-off and demonstrate (via LOSO validation) that our Privacy-Aware (PA) model achieves performance statistically indistinguishable from a non-private model, proving that utility does not require sacrificing privacy. Feature importance analysis highlights that recreational activity time, working time, and travel time play a significant role in stress recognition.

Citations

• AWARE Narrator and the Utilization of Large Language Models to Extract Behavioral Insights from Smartphone Sensing Data
• Semantic Trajectory Data Mining with LLM-Informed POI Classification
• Inverting Gradients -- How easy is it to break privacy in federated learning?
• Deep Leakage from Gradients
• VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition

Related

• Privacy-Enhancing Context Authentication from Location-Sensitive Data
• Learning Location from Shared Elevation Profiles in Fitness Apps: A Privacy Perspective
• Quantifying the Tradeoff Between Cybersecurity and Location Privacy
• Privacy-Aware Adversarial Network in Human Mobility Prediction
• Privacy-Aware Human Mobility Prediction via Adversarial Networks