A talk I gave for Cylab in Feb 2011 on location privacy, summarizing some of my group's work in this area. I discuss some system architectures for location-based content (using pre-fetching and caching to manage privacy), why people use foursquare, and some empirical work on location sharing.
Back in 1989, Magellan released the first commercial handheld GPS device. Now fast-forward twenty years and today we have highly accurate positioning technology, like GPS, readily available in mobile phones. Just last year, approximately 150 million GPS-equipped phones were shipped and, over the next few years, this number is expected to continue growing.
This trend has made location-aware technology much more accessible than before. And the result is clear: more location-based services are being deployed. Some of these are what I would refer to as “location-aware”, which is to say that they simple use your location in order to provide some kind of lookup service. Services like Yelp and Where would fall under this category. However, there is an emerging class of services which I refer to as “social location-sharing applications”.
Foursquare is first really widely adopted lbs that isn’t navigation
approach and style: hci / systems / machine learning how you get location placelab where and how stored cache when shared (rules - who when where activity) locaccino / mobile messaging / social sharing / entropy how displayed passive-active / place naming how used foursquare study
approach and style: hci / systems / machine learning how you get location placelab where and how stored cache when shared (rules - who when where activity) locaccino / mobile messaging / social sharing / entropy how displayed passive-active / place naming how used foursquare study
Tor issues: performance hit, potential issues if poor network speed, and doesn’t work well for paid accounts
approach and style: hci / systems / machine learning how you get location placelab where and how stored cache when shared (rules - who when where activity) locaccino / mobile messaging / social sharing / entropy how displayed passive-active / place naming how used foursquare study
approach and style: hci / systems / machine learning how you get location placelab where and how stored cache when shared (rules - who when where activity) locaccino / mobile messaging / social sharing / entropy how displayed passive-active / place naming how used foursquare study
Entropy related to location privacy Fewer concerns in “public” places
What this means is, just looking at very obvious properties of the co-locations histories doesn't really tell you very much. Also, notice most of the performance boost is at low levels of recall. so if you want to build a high-precision classifier this is the best approach. Really there are two stories here. first it's that the intensity features do not really provide much of a gain over just looking at the number of locations, especially at high recall levels. Second, is that location based features significantly improves performance. This validates that these are clearly good things to look at when you're analyzing this kind of data
What this means is, just looking at very obvious properties of the co-locations histories doesn't really tell you very much. Also, notice most of the performance boost is at low levels of recall. so if you want to build a high-precision classifier this is the best approach. Really there are two stories here. First it's that the intensity features (time spent co-located) do not really provide much of a gain over just looking at the number of locations, especially at high recall levels. Second, is that location based features (ie entropy) significantly improves performance. This validates that these are clearly good things to look at when you're analyzing this kind of data
Entropy related to location privacy Fewer concerns in “public” places
http://www.wired.com/gadgets/wireless/magazine/17-02/lp_guineapig Friedland, Gerald, and Robin Sommer. 2010. Cybercasing the Joint: On the Privacy Implications of Geo-Tagging. In 5th Usenix Hot Topics in Security Workshop (HotSec2010) . http://www.usenix.org/events/hotsec10/tech/full_papers/Friedland.pdf.