Hiding in Plain Sight: Query Obfuscation via Random Multilingual Searches

2025-06-05

AI Summary

To address privacy leakage and filter bubble formation arising from user profile construction in personalized search, this paper proposes a lightweight, imperceptible client-side query obfuscation mechanism: it actively injects randomly generated multilingual noise queries alongside the user’s genuine query to disrupt search engines’ interest modeling. The method requires no server-side infrastructure modifications, operates without user identity identifiers, and supports autonomous client deployment. Its key innovation lies in introducing the first client-side obfuscation paradigm based on randomized multilingual noise, enabling proactive overwriting of existing user profiles. Empirical evaluation on Seznam.cz demonstrates that genuine search result stability remains high at 92.3%, while the search engine’s inferred user interests deviate by as much as 73.1%, effectively impeding accurate user profile reconstruction.

Technology Category

• Search and Optimization: Distributed Search
• Machine Learning: Privacy
• Data Mining & Knowledge Management: Intelligent Query Processing

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Modern search engines extensively personalize results by building detailed user profiles based on query history and behaviour. While personalization can enhance relevance, it introduces privacy risks and can lead to filter bubbles. This paper proposes and evaluates a lightweight, client-side query obfuscation strategy using randomly generated multilingual search queries to disrupt user profiling. Through controlled experiments on the Seznam.cz search engine, we assess the impact of interleaving real queries with obfuscating noise in various language configurations and ratios. Our findings show that while displayed search results remain largely stable, the search engine's identified user interests shift significantly under obfuscation. We further demonstrate that such random queries can prevent accurate profiling and overwrite established user profiles. This study provides practical evidence for query obfuscation as a viable privacy-preserving mechanism and introduces a tool that enables users to autonomously protect their search behaviour without modifying existing infrastructure.

Problem

• Preventing user profiling by search engines
• Disrupting filter bubbles via query obfuscation
• Enhancing privacy with multilingual search noise

Innovation

• Random multilingual queries for obfuscation
• Client-side lightweight privacy protection
• Overwrites user profiles with noise