Publication Type : Journal Article
Publisher : Communications in Computer and Information Science, Springer Verlag
Source : Communications in Computer and Information Science, Springer Verlag, Volume 746, p.226-235 (2017)
ISBN : 9789811068973
Keywords : Auto encoders, Classification (of information), Computer crime, Convolutional neural network, Deep learning, Internet protocols, Learning systems, malware, Malware classifications, Network applications, Network protocols, Network security, Neural networks, Protocol classification
Campus : Coimbatore
School : School of Engineering
Center : Computational Engineering and Networking
Department : Computer Science, Electronics and Communication
Year : 2017
Abstract : In this paper, we present the results obtained by applying deep learning techniques to classification of network protocols and applications using flow features and data signatures. We also present a similar classification of malware using their binary files. We use our own dataset for traffic identification and Microsoft Kaggle dataset for malware classification tasks. The current techniques used in network traffic analysis and malware detection is time consuming and beatable as the precise signatures are known. Deep learned features in both cases are not hand crafted and are learned form data signatures. It cannot be understood by the attacker or the malware in order to fake or hide it and hence cannot be bypassed easily.
Cite this Research Publication : R. K. Rahul, Anjali, T., Menon, V. K., and Dr. Soman K. P., “Deep Learning for Network Flow Analysis and Malware Classification”, Communications in Computer and Information Science, vol. 746, pp. 226-235, 2017.