Encrypted Traffic Classification of Decentralized Applications on Ethereum using Feature Fusion

With the prevalence of blockchain, more and more Decentralized Applications (DApps) are deployed on Ethereum to achieve the goal of communicating without supervision. Users habits may be leaked while these applications adopt SSL/TLS to encrypt their transmission data. Encrypted protocol and the same blockchain platform bring challenges to the traffic classification of DApps. Existing encrypted traffic classification methods suffer from low accuracy in the situation of DApps. In this paper, we design an efficient method to fuse features of different dimensions for DApp fingerprinting. We firstly analyze the reason why existing methods do not perform well before proposing to merge features of different dimensions. Then we fuse these features by a kernel function and propose a fusion feature selection method to select appropriate features to fuse. Applying features that have been fused to the machine learning algorithm can construct a strong classifier. The experiment results show that the accuracy of our method can reach more than 90%, which performs better than state-of-the-art classification approaches.

[1]  Mohsen Guizani,et al.  Transactions papers a routing-driven Elliptic Curve Cryptography based key management scheme for Heterogeneous Sensor Networks , 2009, IEEE Transactions on Wireless Communications.

[2]  Liehuang Zhu,et al.  Certificate-aware encrypted traffic classification using Second-Order Markov Chain , 2016, 2016 IEEE/ACM 24th International Symposium on Quality of Service (IWQoS).

[3]  Jiankun Hu,et al.  Cloud-Based Approximate Constrained Shortest Distance Queries Over Encrypted Graphs With Privacy Protection , 2018, IEEE Transactions on Information Forensics and Security.

[4]  Douglas J. Leith,et al.  A Web Traffic Analysis Attack Using Only Timing Information , 2014, IEEE Transactions on Information Forensics and Security.

[5]  Liehuang Zhu,et al.  Classification of Encrypted Traffic With Second-Order Markov Chains and Application Attribute Bigrams , 2017, IEEE Transactions on Information Forensics and Security.

[6]  Yong Liao,et al.  SAMPLES: Self Adaptive Mining of Persistent LExical Snippets for Classifying Mobile Application Traffic , 2015, MobiCom.

[7]  Rami Puzis,et al.  Transfer Learning for User Action Identication in Mobile Apps via Encrypted Trafc Analysis , 2018, IEEE Intelligent Systems.

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

[9]  S A R A H M E I K L E J O H N,et al.  A Fistful of Bitcoins Characterizing Payments Among Men with No Names , 2013 .

[10]  Andrzej Duda,et al.  Markov chain fingerprinting to classify encrypted traffic , 2014, IEEE INFOCOM 2014 - IEEE Conference on Computer Communications.

[11]  Petar Popovski,et al.  Analysis of the Communication Traffic for Blockchain Synchronization of IoT Devices , 2017, 2018 IEEE International Conference on Communications (ICC).

[12]  Bhavani M. Thuraisingham,et al.  Adaptive encrypted traffic fingerprinting with bi-directional dependence , 2016, ACSAC.

[13]  Mohsen Guizani,et al.  Privacy-Preserving DDoS Attack Detection Using Cross-Domain Traffic in Software Defined Networks , 2018, IEEE Journal on Selected Areas in Communications.

[14]  Nino Vincenzo Verde,et al.  Analyzing Android Encrypted Network Traffic to Identify User Actions , 2016, IEEE Transactions on Information Forensics and Security.

[15]  Xiaojiang Du,et al.  Security in wireless sensor networks , 2008, IEEE Wireless Communications.

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

[17]  Tao Wang,et al.  On Realistically Attacking Tor with Website Fingerprinting , 2016, Proc. Priv. Enhancing Technol..

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

[19]  Eduardo Rocha,et al.  A Survey of Payload-Based Traffic Classification Approaches , 2014, IEEE Communications Surveys & Tutorials.

[20]  Vitaly Shmatikov,et al.  Beauty and the Burst: Remote Identification of Encrypted Video Streams , 2017, USENIX Security Symposium.

[21]  Patrick D. McDaniel,et al.  An Analysis of Anonymity in Bitcoin Using P2P Network Traffic , 2014, Financial Cryptography.

[22]  Giuseppe Aceto,et al.  PortLoad: Taking the Best of Two Worlds in Traffic Classification , 2010, 2010 INFOCOM IEEE Conference on Computer Communications Workshops.

[23]  Mohsen Guizani,et al.  Privacy-Preserving Support Vector Machine Training Over Blockchain-Based Encrypted IoT Data in Smart Cities , 2019, IEEE Internet of Things Journal.

[24]  Nuno Santos,et al.  Effective Detection of Multimedia Protocol Tunneling using Machine Learning , 2018, USENIX Security Symposium.

[25]  Xiaojiang Du,et al.  A survey of key management schemes in wireless sensor networks , 2007, Comput. Commun..

[26]  Mauro Conti,et al.  AppScanner: Automatic Fingerprinting of Smartphone Apps from Encrypted Network Traffic , 2016, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).

[27]  Mohsen Guizani,et al.  An effective key management scheme for heterogeneous sensor networks , 2007, Ad Hoc Networks.