Bloom Cookies: Microsoft researchers have managed to develop an algorithm that is capable of eliminating the display of web search results for any user without using existing technology.
The idea, which will be presented next month under the title Bloom Cookies: Web Search Personalisation without User Tracking, uses a new type of cookie that can highly encode user profiles to preserve their privacy without having to stop their online habits.
“The design of Bloom Cookies is inspired by our analysis of a large set of search result logs that shows the drawbacks of the two-profile obfuscation technique, i.e. a general profile and another one designed for noise injection, currently used by many privacy-preserving personalization systems,” the researchers said in the project summary.
“We believe that the general profile generalization fails to protect users from a server that can link user sessions over time.”
“Noise can address these problems, but at a cost to communication and generally the noise would have to be generated by a trusted third party.”
Bloom Cookies, said Nitesh Mor, John Kubiatowicz of the University of California, Oriana Riva, and Suman Nath of Microsoft Research, will use Bloom filters to achieve a better trade-off between privacy, personalization, and network efficiency.
"We will provide you with similar or better personalization and privacy protection from noise injection and generic profiles, without any cost to your communication and no dictionary to generate noise," the researchers said.
It is unclear whether this approach can “work together” with Bing and its tracking capabilities.
Microsoft's project will be published at the NDSS Symposium to be held in San Diego.
