Authors: Nana Wang, Mohan Kankanhalli

Published on: April 22, 2024

Impact Score: 7.8

Arxiv code: Arxiv:2404.14106

Summary

• What is new: DPTraj-PM introduces a novel method for synthesizing trajectory data with strong privacy guarantees while preserving the data’s utility.
• Why this is important: The release of trajectory data raises privacy concerns, and previous methods did not adequately protect privacy or maintain data utility.
• What the research proposes: DPTraj-PM, combining a prefix tree structure and an m-order Markov process within the differential privacy framework, to model and synthesize trajectory data.
• Results: DPTraj-PM outperforms existing techniques in preserving data utility while ensuring privacy, demonstrated through experiments on real-world datasets.

Technical Details

Technological frameworks used: Differential Privacy

Models used: Prefix tree structure and m-order Markov process

Data used: GPS trajectory data

Potential Impact

Transportation planning, epidemic modeling, location-based services, and data analytics firms

Want to implement this idea in a business?

We have generated a startup concept here: PathGuard.