Researchers from Rutgers University have been testing out the theory that speed information matched against road topology provides enough information to be able to figure out a driver’s final location. The research sprung out of the speed data collected by insurance companies to monitor its customer’s driving habits in order to adjust rates. Customers can opt-in to “usage-based” automotive insurance programs that install a data collection device in their cars that only collects speed information. Insurance companies that monitor the detailed speed data assure their customers that privacy concerns are offset by the fact that no locational information is collected as part of the program. This assurance, according to the Rutgers researchers, is erroneous.
In the technical report published by Bernhard Firner, Shridatt Sugrim, Yulong Yang, and Janne Lindqvist, the researchers point out:
Today people increasingly have the opportunity to opt-in to “usage-based” automotive insurance programs for reducing insurance premiums. In these programs, participants install devices in their vehicles that monitor their driving behavior, which raises some privacy concerns. Some devices collect fine-grained speed data to monitor driving habits. Companies that use these devices claim that their approach is privacy-preserving because speedometer measurements do not have physical locations. However, we show that with knowledge of the user’s home location, as the insurance companies have, speed data is sufficient to discover driving routes and destinations when trip data is collected over a period of weeks.
The researchers were able to develop an algorithm that matches the changes in speed of vehicles in order to determine whether the car made any turns. Using a approach they named “elastic pathing” the processes “pins” the route to the road depending on the speed of the vehicle and information about the road’s topology. To test out the algorithm, the researchers compared speed data from seven drivers travelling from their homes to 46 unique destinations over 240 journeys. The calculated routes from the algorithm were compared against GPS locational data collected by those same drivers for those journeys. The end results was that the researchers were able “to predict trip destinations to within 250 meters of ground truth in 10% of the traces and within 500 meters in 20% of the traces.”
References
Free weekly newsletter
Fill out your e-mail address to receive our newsletter!
By entering your email address you agree to receive our newsletter and agree with our privacy policy.
You may unsubscribe at any time.
Firner, Bernhard, Shridatt Sugrim, Yulong Yang, and Janne Lindqvist. “Elastic Pathing: Your Speed Is Enough to Track You.” ArXiv:1401.0052. Cornell University Library, 30 Dec. 2013. Web. 23 Jan. 2014. <http://arxiv.org/abs/1401.0052>.
“How To Track Vehicles Using Speed Data Alone.” MIT Technology Review. MIT, 7 Jan. 2014. Web. 23 Jan. 2014. <http://www.technologyreview.com/view/523346/how-to-track-vehicles-using-speed-data-alone/>.
