Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929751639195648 |
|---|---|
| author | Hsu, I-Jung Lin, Chih-Hsun Yu, Chia-Mu Kuo, Sy-Yen Huang, Chun-Ying |
| author_facet | Hsu, I-Jung Lin, Chih-Hsun Yu, Chia-Mu Kuo, Sy-Yen Huang, Chun-Ying |
| contents | 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 \textsc{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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07483 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data Hsu, I-Jung Lin, Chih-Hsun Yu, Chia-Mu Kuo, Sy-Yen Huang, Chun-Ying Cryptography and Security Machine Learning 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 \textsc{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. |
| title | Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2503.07483 |