Secured release of search queries, clicks and counts

Text mining refers to extracting or mining information from large amounts of text based documents and the security deals with safeguarding the useful informations. Search engines such as Bing, Google, or Yahoo log interactions with their users. When a user submits a query and clicks on one or more results, a new entry is added to the search log. However these search engine companies are aware of publishing search logs in order not to disclose sensitive information. The goal of this project is to publish frequent items (utility) without disclosing sensitive information about the users (privacy). The existing proposals to achieve k-anonymity in search logs are insufficient in the light of attackers who can actively influence the search log and its impossibility to achieve good utility with differential privacy. This project propose a novel algorithm ZEALOUS and show how to set its parameters to guarantee probabilistic differential privacy. It compares the probabilistic differential privacy with indistinguishablity. This project concludes with an extensive experimental evaluation, by comparing the utility of various algorithms that guarantee anonymity or privacy in search log publishing. This evaluation includes applications that use search logs for improving both search experience and search performance, and the results show that ‘ZEALOUS’ output is sufficient for these applications by achieving strong formal privacy guarantees.