Query Obfuscation Semantic Decomposition

TL;DR

This paper introduces a query obfuscation technique using semantic decomposition with related and distractor terms, aiming to protect user privacy while maintaining search result accuracy.

Contribution

It presents a novel method combining word embeddings and semantic decomposition to enhance privacy in search queries without losing result relevance.

Findings

The method accurately reconstructs search results from decomposed queries.

It effectively balances privacy protection with search result fidelity.

The approach is robust against clustering-based de-anonymization attacks.

Abstract

We propose a method to protect the privacy of search engine users by decomposing the queries using semantically \emph{related} and unrelated \emph{distractor} terms. Instead of a single query, the search engine receives multiple decomposed query terms. Next, we reconstruct the search results relevant to the original query term by aggregating the search results retrieved for the decomposed query terms. We show that the word embeddings learnt using a distributed representation learning method can be used to find semantically related and distractor query terms. We derive the relationship between the \emph{obfuscity} achieved through the proposed query anonymisation method and the \emph{reconstructability} of the original search results using the decomposed queries. We analytically study the risk of discovering the search engine users' information intents under the proposed query obfuscation method, and empirically evaluate its robustness against clustering-based attacks. Our experimental results show that the proposed method can accurately reconstruct the search results for user queries, without compromising the privacy of the search engine users.