The Tor anonymity system provides online privacy for millions of users, but it is slower than typical web browsing. To improve Tor performance, we propose PredicTor, a path selection technique that uses a Random Forest classifier trained on recent measurements of Tor to... View more
 JANSEN, R., GEDDES, J., WACEK, C., SHERR, M., AND SYVERSON, P. Never Been KIST: Tor's Congestion Management Blossoms with Kernel-Informed Socket Transport. In Proceedings of the 23rd USENIX Security Symposium (USENIX Security'14).
 MITCHELL, T. Machine Learning. McGraw-Hill, 1997.
 MURDOCH, S. J., AND WATSON, R. N. Metrics for Security and Performance in Low-Latency Anonymity Systems. In Proceedings of the 8th International Symposium on Privacy Enhancing Technologies (PETS'08).
 SYVERSON, P. Why I'm not an entropist. In International Workshop on Security Protocols (2009), Springer, pp. 213-230.
 TORPS. TorPS: The Tor path simulator., http://torps.github.io. In Table 1, we show the median and 90th percentile performance and circuit distance improvements for PredicTor compared to Vanilla.