Researchers from Imperial College London and Université Catholique de Louvain discovered a noise-exploitation attack to break through query-based databases that use aggregation and noise to mask personal data, TechCrunch reports. Imperial College London Assistant Professor and co-author of the research paper Yves-Alexandre de Montjoye said a party could exploit differential privacy should they send enough queries to eventually figure out “every single thing that exists in the database because every time you give me a bit more information. We start from one query and then we do a variation of it and by studying the differences between the queries we know that some of the noise will disappear, some of the noise will not disappear and by studying noise that does not disappear basically we figure out the sensitive information.”
Full Story