Depersonalization of Location Traces
Event details
| Date | 26.06.2009 |
| Hour | 11:15 |
| Speaker | Prof. Marco Gruteser, Rutgers University, NJ, USA |
| Location | |
| Category | Conferences - Seminars |
Motivated by a probe-vehicle based automotive traffic monitoring system, this talk addresses the problem of guaranteeing anonymity in a dataset of location traces while maintaining high data accuracy. An analysis of a set of GPS traces from 239 vehicles shows that known privacy algorithms cannot meet application accuracy requirements or fail to provide privacy guarantees for drivers in low-density areas. To overcome these challenges, I will present a novel time-to-confusion criterion to characterize privacy in a location dataset and propose a centralized density-aware path cloaking algorithm that hides location samples in a dataset to provide a time-to-confusion guarantee for all vehicles. This approach effectively guarantees worst case tracking bounds, while achieving significant data accuracy improvements. I will then discuss a distributed scheme building on virtual trip lines, which does not need to rely on a trustworthy privacy server with access to all traces.
Prof. Gruteser's homepage
Practical information
- General public
- Free