Evaluating Differential Privacy Approaches for Query Obfuscation in Information Retrieval

Protecting the privacy of a user while they interact with an Information Retrieval (IR) system is crucial. This becomes more challenging when the IR system is not cooperative in satisfying the user’s privacy needs. Recent advancements in Natural Language Processing (NLP) have demonstrated Differential Privacy’s (DP) effectiveness in safeguarding text privacy for tasks like spam detection and sentiment analysis, even under the assumption of a non-cooperative system. Our investigation explores if DP methods, originally designed for specific NLP tasks, can effectively obscure queries in IR. Our analyses show that using the Vickrey DP mechanism, employing the Mahalanobis norm with a privacy budget ranging from ε = 10 to 12.5, provides cutting-edge privacy protection and enhances effectiveness. Unlike previous methods, DP allows users to fine-tune their desired level of privacy by adjusting the privacy budget ε. This flexibility offers a balance between how effective the system is and how much privacy is maintained, unlike the more rigid nature of previous approaches.