Experimental evaluation of privacy-preserving profiling schemes on PlanetLab

New pervasive technologies often reveal many sensitive information about users' habits, seriously compromising the privacy and sometimes even the personal security of people. To cope with this problem, researchers have developed the idea of privacy-preserving data mining which refers to the possibility of releasing aggregate information about the data provided by multiple users, without any information leakage about individual data. These techniques have different privacy levels and communication costs, but all of them can suffer when some users' data becomes inaccessible during the operation of the privacy preserving protocols. It is thus interesting to validate the applicability of such architectures in real-world scenarios. In this paper we experimentally evaluate two promising privac-preserving techniques on PlanetLab, analyzing the execution time and the failure rate that each scheme exhibits.