Data Poisoning Attacks to Locally Differentially Private Range Query Protocols

2025-03-05

AI Summary

This work exposes a critical vulnerability of Local Differential Privacy (LDP) trajectory protocols to data poisoning attacks in range query settings: an adversary can significantly inflate the frequency of a target pattern in the perturbed aggregate result by injecting only a small number of fabricated trajectories. To address this, the authors conduct the first systematic analysis of poisoning vulnerabilities in LDP trajectory protocols and propose TraP—a heuristic attack framework that generates efficient synthetic trajectories based on prefix-suffix patterns. TraP achieves high attack success while reducing computational complexity by an order of magnitude. Experiments on real-world trajectory datasets demonstrate that TraP attains over a fivefold increase in the target pattern’s frequency using fewer than 1% poisoned users, revealing a fundamental security flaw in existing LDP trajectory mechanisms under practical deployment conditions.

Technology Category

• Machine Learning: Privacy
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Natural Language Processing: Safety and Robustness

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Trajectory data, which tracks movements through geographic locations, is crucial for improving real-world applications. However, collecting such sensitive data raises considerable privacy concerns. Local differential privacy (LDP) offers a solution by allowing individuals to locally perturb their trajectory data before sharing it. Despite its privacy benefits, LDP protocols are vulnerable to data poisoning attacks, where attackers inject fake data to manipulate aggregated results. In this work, we make the first attempt to analyze vulnerabilities in several representative LDP trajectory protocols. We propose extsc{TraP}, a heuristic algorithm for data underline{P}oisoning attacks using a prefix-suffix method to optimize fake underline{Tra}jectory selection, significantly reducing computational complexity. Our experimental results demonstrate that our attack can substantially increase target pattern occurrences in the perturbed trajectory dataset with few fake users. This study underscores the urgent need for robust defenses and better protocol designs to safeguard LDP trajectory data against malicious manipulation.

Problem

• Analyzing vulnerabilities in LDP trajectory protocols.
• Proposing TraP for efficient data poisoning attacks.
• Highlighting need for robust defenses against malicious manipulation.

Innovation

• Analyzes vulnerabilities in LDP trajectory protocols
• Proposes TraP algorithm for optimized fake trajectory selection
• Demonstrates significant impact with minimal fake users