A Novel Methodology for Detecting the Network Obtrusion Based on Deep Learning
M. Prabu1, Ch. Sai Chaitanya2, Chandini Singh3, Ritu Gupta4, Pranjal Sharma5
1M.Prabu, Assistant Professor(O.G), Department of Computer Science and Engineering, Ramapuram Campus, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India.
2Ch. Sai Chaitanya, Student, Department of Computer Science and Engineering, Ramapuram Campus, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India.
3Chandini Singh, Student, Department of Computer Science and Engineering, Ramapuram Campus, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India.
4Ritu Gupta, Student, Department of Computer Science and Engineering, Ramapuram Campus, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India.
5Pranjal Sharma, Student, Department of Computer Science and Engineering, Ramapuram Campus, SRM Institute of Science and Technology, Chennai (Tamil Nadu), India.
Manuscript received on 18 April 2019 | Revised Manuscript received on 25 April 2019 | Manuscript published on 30 April 2019 | PP: 1612-1617 | Volume-8 Issue-4, April 2019 | Retrieval Number: D6728048419/19©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: With the expanding number of PCs being associated with the Internet, the risk for security of data as well as intrusions is ever increasing. Since,no system can be a 100% secure, it is essential for a proposed system to be well tested and evaluated in terms of security. Hence, this paper proposes a Network Obtrusion Detection System (NODS), which specifically addresses the risks of network intrusions.The proposed framework regularly searches the network for any unusual activity.Although the unusual activity can also be system generated and be harmless, which makes this a difficult detection, the system makes best possible effort to ensure security. Neural framework with its capability of learning has ended up being a champion among the most promising methods to deal with this issue This paper also exhibits a review of neural systems and their utilization in building inconsistency interruption frameworks.The system makes use of Non-Symmetric deep autoencoders (NDAE)s, which make use of techniques such as deep learning. Although the system has scopes of improvements, it has shown promising results so far.
Keywords: Profound Adapting, Inconsistency Recognition, Auto-Encoders, KDD, Arrange Security.
Scope of the Article: Deep Learning