Personal Data Utilization and Privacy Protection

Pricing Mechanisms in Personal Data Market


Differentially Private Real-time Data Publishing

  Recent emerging mobile and wearable technologies make it easy to collect personal spatiotemporal data such as activity trajectories in daily life. Publishing real-time statistics over trajectory streams produced by crowds of people is expected to be valuable for both academia and business, answering questions such as “How many people are in Kyoto Station now?” However, analyzing these raw data will entail risks of compromising individual privacy. Ɛ-Differential Privacy has emerged as a de facto standard for private statistics publishing because of its guarantee of being rigorous and mathematically provable. It is also considered as a theoretical model which is hard to be deployed in a industrial scenario. For infinite trajectory streams, it is difficult to protect every infinite trajectory under Ɛ-differential privacy, and maintain acceptable data utility. On the other hand, in real-life, not all users require the same level of privacy. To this end, we propose a flexible user-level privacy model of ℓ-trajectory privacy to ensure every length of ℓ trajectories under protection of Ɛ-differential privacy. Each user can specifies a value of ℓ as his/her privacy level. We also design an algorithmic framework to publish ℓ-trajectory private data in real-time. Experiments using real-life datasets show that our proposed algorithms are effective and efficient.