Don't let Google know I'm lonely!
This addresses privacy concerns for users of online systems by improving detection of personal profiling, though it appears incremental as it builds on existing privacy concepts.
The paper tackles the problem of detecting sensitive topic profiling by online systems, proposing a definition called ε-indistinguishability and constructing scalable tools to assess adversaries' learning potential, achieving a detection rate of over 98% for sensitive topics in experiments.
From buying books to finding the perfect partner, we share our most intimate wants and needs with our favourite online systems. But how far should we accept promises of privacy in the face of personal profiling? In particular we ask how can we improve detection of sensitive topic profiling by online systems? We propose a definition of privacy disclosure we call ε-indistinguishability from which we construct scalable, practical tools to assess an adversaries learning potential. We demonstrate our results using openly available resources, detecting a learning rate in excess of 98% for a range of sensitive topics during our experiments.