Traffic Analysis with Deep Learning

Deep Neural Networks (DNN) has obtained enormous attention with its advantageous feature learning and its powerful prediction ability. In this paper, we broadly study the applicability of deep learning to traffic analysis and present its effectiveness on the feature extraction for state-of-the-art machine learning algorithms, website and keyword fingerprinting attacks, and the prediction on the fingerprintability of websites. To the best of our knowledge, this is the first extensive work to introduce various applications using DNN in traffic analysis. With great help of DNN, the quality of cutting edge website fingerprinting attacks is upgraded while the feature dimension becomes much lower. As the classifiers, DNN successfully detects which website the user visited among 100 websites with 91% TPR and 1% FPR against 100,000 background websites, and as the fingerprintability predictors, it almost perfectly determines the fingerprintability of 4,500 website traffic instances with 99% of accuracy.

[1]  Kenneth O. Stanley and Bobby D. Bryant and Risto Miikkulainen,et al.  Real-Time Evolution in the NERO Video Game (Winner of CIG 2005 Best Paper Award) , 2005, CIG.

[2]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[3]  Shuai Li,et al.  Fingerprinting Keywords in Search Queries over Tor , 2017, Proc. Priv. Enhancing Technol..

[4]  George Danezis,et al.  k-fingerprinting: A Robust Scalable Website Fingerprinting Technique , 2015, USENIX Security Symposium.

[5]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[6]  Klaus Wehrle,et al.  Website Fingerprinting at Internet Scale , 2016, NDSS.

[7]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[8]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[9]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[10]  Tao Wang,et al.  Effective Attacks and Provable Defenses for Website Fingerprinting , 2014, USENIX Security Symposium.

[11]  Thomas Ristenpart,et al.  Peek-a-Boo, I Still See You: Why Efficient Traffic Analysis Countermeasures Fail , 2012, 2012 IEEE Symposium on Security and Privacy.

[12]  Will Song,et al.  End-to-End Deep Neural Network for Automatic Speech Recognition , 2015 .

[13]  Tao Wang,et al.  Walkie-Talkie: An Efficient Defense Against Passive Website Fingerprinting Attacks , 2017, USENIX Security Symposium.

[14]  Wouter Joosen,et al.  Automated Feature Extraction for Website Fingerprinting through Deep Learning. , 2017 .

[15]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[16]  Pierre Baldi,et al.  Autoencoders, Unsupervised Learning, and Deep Architectures , 2011, ICML Unsupervised and Transfer Learning.

[17]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[19]  Yoshua Bengio,et al.  Scaling learning algorithms towards AI , 2007 .

[20]  R. Zemel,et al.  THE VARIATIONAL FAIR AUTO ENCODER , 2015 .

[21]  Lawrence D. Jackel,et al.  Handwritten Digit Recognition with a Back-Propagation Network , 1989, NIPS.

[22]  Tao Wang,et al.  A Systematic Approach to Developing and Evaluating Website Fingerprinting Defenses , 2014, CCS.

[23]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

[24]  B. H. Blott,et al.  Review of neural network applications in medical imaging and signal processing , 1992, Medical and Biological Engineering and Computing.

[25]  Thomas Engel,et al.  Website fingerprinting in onion routing based anonymization networks , 2011, WPES.

[26]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[27]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .