Efficient Utility Improvement for Location Privacy

Abstract

Abstract:The continuously increasing use of locationbased services poses an important threat to the privacy of users. A natural defense is to employ an obfuscation mechanism, such as those providing geoindistinguishability, a framework for obtaining formal privacy guarantees that has become popular in recent years. Ideally, one would like to employ an optimal obfuscation mechanism, providing the best utility among those satisfying the required privacy level. In theory optimal mechanisms can be constructed via linear programming. In practice, however, this is only feasible for a radically small number of locations. As a consequence, all known applications of geo-indistinguishability simply use noise drawn from a planar Laplace distribution. In this work, we study methods for substantially improving the utility of location obfuscation, while maintaining practical applicability as a main goal. We provide such solutions for both infinite (continuous or discrete) as well as large but finite domains of locations, using a Bayesian remapping procedure as a key ingredient. We evaluate our techniques in two real world complete datasets, without any restriction on the evaluation area, and show important utility improvements with respect to the standard planar Laplace approach.

Rethinking Location Privacy for Unknown Mobility Behaviors

“…6b), and thus achieve very low privacy. This experiment shows that training an optimal sporadic LPPM with location data from other users (e.g., [8]) is very dangerous from a privacy standpoint.…”

“…We now describe a framework that instantiates the abstraction above. This framework extends ideas from [1], [8]. It consists of two steps: the design step, where the user designs Adversary's estimate of the real location x s using z r .…”

“…Remapping Techniques. In [8], Chatzikokolakis et al propose a technique called optimal remapping that provides an average loss improvement for any memoryless LPPM, without reducing privacy. They proposed this method under the hardwired sporadic mobility model.…”

Trading Optimality for Performance in Location Privacy

“…There is, therefore, a growing interest in the development of mechanisms to protect location privacy during the use of LBSs. Most of the approaches in the literature are based on perturbing the user's location, see, for instance, [1,2,5,6]. Obviously, the perturbation must be done with care, in order to preserve the utility of the service.…”

Location histogram privacy by Sensitive Location Hiding and Target Histogram Avoidance/Resemblance

“…RO is applied to the histogram H = (7, 2, 3, 2, 13, 12, 8, 3) inFigure 1a, using the target histogram H =(10,8,6,2,13,4,4,3) in…”