Leveraging Functional Encryption and Deep Learning for Privacy-Preserving Traffic Forecasting

2025-04-17

AI Summary

To address the inherent trade-off between driver location privacy and model accuracy in traffic flow forecasting, this paper proposes a privacy-preserving encrypted-domain traffic flow prediction framework. Methodologically, it introduces the first integration of functional encryption (FE) with *k*-anonymity for location aggregation, enabling secure spatiotemporal data aggregation directly over ciphertexts; additionally, it designs a hybrid Conv-LSTM and Bi-LSTM architecture to jointly capture road network spatial locality, short-term dynamics, and long-term temporal trends. Experiments on real-world traffic datasets demonstrate that the system achieves an average absolute error below 10% within a 60-minute prediction horizon, without ever decrypting raw trajectory data—thereby eliminating individual location leakage risks. The primary contributions are: (i) the first application of functional encryption to encrypted-domain spatiotemporal aggregation in traffic forecasting; and (ii) an end-to-end, high-accuracy framework supporting both real-time and long-horizon joint prediction under rigorous privacy guarantees.

Technology Category

• Machine Learning: Privacy
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Application Domains: Transportation

Application Category

• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Over the past few years, traffic congestion has continuously plagued the nation's transportation system creating several negative impacts including longer travel times, increased pollution rates, and higher collision risks. To overcome these challenges, Intelligent Transportation Systems (ITS) aim to improve mobility and vehicular systems, ensuring higher levels of safety by utilizing cutting-edge technologies, sophisticated sensing capabilities, and innovative algorithms. Drivers' participatory sensing, current/future location reporting, and machine learning algorithms have considerably improved real-time congestion monitoring and future traffic management. However, each driver's sensitive spatiotemporal location information can create serious privacy concerns. To address these challenges, we propose in this paper a secure, privacy-preserving location reporting and traffic forecasting system that guarantees privacy protection of driver data while maintaining high traffic forecasting accuracy. Our novel k-anonymity scheme utilizes functional encryption to aggregate encrypted location information submitted by drivers while ensuring the privacy of driver location data. Additionally, using the aggregated encrypted location information as input, this research proposes a deep learning model that incorporates a Convolutional-Long Short-Term Memory (Conv-LSTM) module to capture spatial and short-term temporal features and a Bidirectional Long Short-Term Memory (Bi-LSTM) module to recover long-term periodic patterns for traffic forecasting. With extensive evaluation on real datasets, we demonstrate the effectiveness of the proposed scheme with less than 10% mean absolute error for a 60-minute forecasting horizon, all while protecting driver privacy.

Problem

• Privacy risks in drivers' location data reporting
• Balancing traffic forecasting accuracy and data privacy
• Secure aggregation of encrypted spatiotemporal location information

Innovation

• Functional encryption for privacy-preserving data aggregation
• Conv-LSTM and Bi-LSTM for traffic forecasting
• k-anonymity scheme to protect driver location privacy