Network Application Identification Using Deep Learning
Anjali T, Department of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chenai (Tamil Nadu), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 510-513 | Volume-8 Issue-5, March 2019 | Retrieval Number: E2982038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The network traffic is increasing exponentially. Managing the vulnerabilities and threats become a major issue due to the heavy volume of data involved. To deal with such problems, network administrators use their experience and understanding of different applications running in their network, to monitor the packet traffic. Here identification and classification of different application that dumps data into the network, becomes challenging. The traditional way is by using behavioral signatures such as port number, application header, transmission frequency, destination IP etc. Although this is still the popular method, it can be beaten by malicious apps and users, by random port changes, proxies, protocol tunneling, and many other tricks. To overcome this issue a technique called flow feature-based analysis can be employed. In this paper, we present a deep learning-based data signature analyses which will identify applications by analyzing the information in traffic flow and some results we have observed. Mainly we are using convolutional neural network based classification and autoencoder based feature extraction to improve the efficiency.
Keyword: Auto Encoders, Convolutional Neural Networks, Deep Learning, Internet Applications, Web Browser.
Scope of the Article: Deep Learning