PredicTor: A Global, Machine Learning Approach to Tor Path Selection
ACM Transactions on Privacy and Security · 31.08.2025 · 28 (3) · 1-31
DOI: 10.1145/3723356 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Privacy and Security, online erschienen am 26.08.2025. Verfasst von Armon Barton und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: National Science Foundation, Rochester Institute of Technology, Signature Interdisciplinary Research Areas.
Abstract (Originalsprache)
Tor users derive anonymity in part from the size of the Tor user base, but Tor struggles to attract and support more users due to performance limitations. Previous works have proposed modifications to Tor’s path selection algorithm to enhance both performance and security, but many proposals have unintended consequences due to incorporating information related to client location. We instead propose selecting paths using a global view of the network, independent of client location, and we propose doing so with a machine learning classifier to predict the performance of a given path before building a circuit. We show through a variety of simulated and live experimental settings, across different time periods, that this approach can significantly improve performance compared to Tor’s default path selection algorithm and two previously proposed approaches. In addition to evaluating the security of our approach with traditional metrics, we propose a novel anonymity metric that captures information leakage resulting from location-aware path selection, and we show that our path selection approach leaks no more information than the default path selection algorithm.
Förderung
- National Science Foundation
- Rochester Institute of Technology
- Signature Interdisciplinary Research Areas
Zitieren
APA
Barton, A., Walsh, T., Imani, M., Ming, J., & Wright, M. (2025). PredicTor: A Global, Machine Learning Approach to Tor Path Selection. ACM Transactions on Privacy and Security, 28(3), 1-31. https://doi.org/10.1145/3723356
Vancouver
Barton A, Walsh T, Imani M, Ming J, Wright M. PredicTor: A Global, Machine Learning Approach to Tor Path Selection. ACM Transactions on Privacy and Security. 2025;28(3):1-31. doi:10.1145/3723356
BibTeX
@article{Barton2025,
author = {Barton, Armon and Walsh, Timothy and Imani, Mohsen and Ming, Jiang and Wright, Matthew},
title = {PredicTor: A Global, Machine Learning Approach to Tor Path Selection},
journal = {ACM Transactions on Privacy and Security},
year = {2025},
volume = {28},
number = {3},
pages = {1--31},
doi = {10.1145/3723356}
}
EUVIMED