Privacy-Aware Human Mobility Prediction via Adversarial Networks

TL;DR

This paper introduces a novel LSTM-based adversarial framework that balances privacy and utility in human mobility data sharing, enabling privacy-preserving representations while maintaining predictive accuracy.

Contribution

It proposes a new adversarial learning architecture with Pareto analysis for privacy-utility trade-off in mobility data, outperforming existing methods.

Findings

Achieves 45% privacy enhancement while maintaining 32% utility.

Demonstrates effectiveness on four mobility datasets.

Provides a Pareto frontier analysis for privacy-utility balancing.

Abstract

As various mobile devices and location-based services are increasingly developed in different smart city scenarios and applications, many unexpected privacy leakages have arisen due to geolocated data collection and sharing. While these geolocated data could provide a rich understanding of human mobility patterns and address various societal research questions, privacy concerns for users' sensitive information have limited their utilization. In this paper, we design and implement a novel LSTM-based adversarial mechanism with representation learning to attain a privacy-preserving feature representation of the original geolocated data (mobility data) for a sharing purpose. We quantify the utility-privacy trade-off of mobility datasets in terms of trajectory reconstruction risk, user re-identification risk, and mobility predictability. Our proposed architecture reports a Pareto Frontier analysis that enables the user to assess this trade-off as a function of Lagrangian loss weight parameters. The extensive comparison results on four representative mobility datasets demonstrate the superiority of our proposed architecture and the efficiency of the proposed privacy-preserving features extractor. Our results show that by exploring Pareto optimal setting, we can simultaneously increase both privacy (45%) and utility (32%).