Seybold Report ISSN: 1533-9211
B.L. Malleswari
Principal & Professor, Department of Electronics and Communication Engineering,
Sridevi Women’s Engineering College, Hyderabad, India, blmalleswari@gmail.com
K. Anusha
U.G Student, Department of Electronics and Communication Engineering,
Sridevi Women’s Engineering College, Hyderabad, India
C. Aakanksha
U.G Student, Department of Electronics and Communication Engineering,
Sridevi Women’s Engineering College, Hyderabad, India
M. Haritha
U.G Student, Department of Electronics and Communication Engineering,
Sridevi Women’s Engineering College, Hyderabad, India
Vol 17, No 07 ( 2022 ) | DOI: 10.5281/zenodo.6875930 | Licensing: CC 4.0 | Pg no: 46-53 | Published on: 25-07-2022
Abstract
In this Paper, Intelligent Intrusion Detection System using deep neural networks is proposed. Because of increase in technologies in our day to day life number of security breaches happening in various parts of the world is also increasing at considerable rate, now this makes us to realise that there is a severe need of strong intrusion detection systems to overcome the problems related to security breaches, in order to do that we propose a hybrid intrusion detection system that can effectively work to detect various malicious activities happening at host level and as well as network level. Different misused detections have been used previously to identify the intruders and their suspect activities performed at host level and network level but many of them failed as they are not accurate, in this paper we proposed a unique model of using Deep neural networks to solve the security breaches problems. We used various set of data sets like NSL and KDD Cup 99 to effectively detect the intrusions happening at different networks. The proposed system meets the higher level of accuracy. It compares the SVM and Random Forest algorithms and has a greater accuracy.
Keywords:
Machine Learning, Deep learning, Neural Network, SVM, Random Forest