Website Privacy Preservation for Query Log Publishing

In this work we study privacy preservation for the publi- cation of search engine query logs. In particular, we introduce a new privacy concern, which is that of website privacy (or business privacy). We define the possible adversaries that could be interested in disclosing website information and the vulnerabilities found in the query log, from which they could benefit. We also detail anonymization techniques to protect website information, and explore the different types of attacks that an adversary could use. We then present a graph-based heuristic to validate the effectiveness of our anonymization method, and perform an experimental evaluation of this approach. Our experimental results show that the query log can be appropriately anonymized against a specific attack for website exposure, by only removing approximately 9% of the total volume of queries and clicked URLs.