Flow correlation is the core technique used in a multitude of deanonymization attacks on Tor. Despite the importance of ow correlation attacks on Tor, existing ow correlation techniques are considered to be ine ective and unreliable in linking Tor ows when applied at a large scale, i.e., they impose high rates of false positive error rates or require impractically long ow observations to be able to make reliable correlations. In this paper, we show that, unfortunately, ow correlation attacks can be conducted on Tor tra c with drastically higher accuracies than before by leveraging emerging learning mechanisms. We particularly design a system, called DeepCorr, that outperforms the state-of-the-art by signicant margins in correlating Tor connections. DeepCorr leverages an advanced deep learning architecture to learn a ow correlation function tailored to Tor's complex network-this is in contrast to previous works' use of generic statistical correlation metrics to correlate Tor ows. We show that with moderate learning, DeepCorr can correlate Tor connections (and therefore break its anonymity) with accuracies signi cantly higher than existing algorithms, and using substantially shorter lengths of ow observations. For instance, by collecting only about 900 packets of each target Tor ow (roughly 900KB of Tor data), DeepCorr provides a ow correlation accuracy of 96% compared to 4% by the state-of-the-art system of RAPTOR using the same exact setting.We hope that our work demonstrates the escalating threat of ow correlation attacks on Tor given recent advances in learning algorithms, calling for the timely deployment of e ective countermeasures by the Tor community.