RePriv, the subject of our recent paper at Oakland S&P, is a browser-based technology that allows for Web personalization, while controlling the release of private information within the browser. We demonstrate how to perform mining of core user interests within a browser. We show that RePriv's default in-browser mining can be done with no noticeable overhead to normal browsing, and that the results it produces converge quickly. We then go on to show similar results for each of our case studies: that RePriv enables high-quality personalization, and that the performance impact each case has on the browser is minimal. We conclude that personalized content and individual privacy on the Web are not mutually exclusive.
While the focus of RePriv is on the browser, more recently, we have also introduced privacy-preserving personalization to mobile devices, by modifying the Windows Phone OS, with exciting results. The user in MoRePriv is classified into one of several profiles called personas. We will describe how MoRePriv applies to both legacy apps through automatic personalization and new phone apps by the operating system exposing personalization APIs.