A HYBRID APPROACH OF INTRUSION DETECTION SYSTEM BASED ON NEURAL NETWORK AND NORMALIZATION

Authors

  • Kavita Patil Department of Computer Science & Engineering Technocrats Institute of Technology, Bhopal RGPV University Bhopal, INDIA
  • Dr. Bhupesh Gour Department of Computer Science & Engineering Technocrats Institute of Technology, Bhopal RGPV University Bhopal, INDIA
  • Mr. Deepak Tomar Department of Computer Science & Engineering Technocrats Institute of Technology, Bhopal RGPV University Bhopal, INDIA

DOI:

https://doi.org/10.24113/ijoscience.v2i2.76

Keywords:

Intrusion, Detection, Attacks, Neural Network, KYOTO.

Abstract

In the whole world, the most famous threat that are spread around is done by the intruder computers over the internet. The types of external activity found over the system are termed as intrusion and the mechanism that is applied for the preservation of the information against these intrusions are called as intrusion detection system. For protecting the network, first there is a need to detect the attacks then take the proper action regarding it. There are techniques applied for scanning and analysing for highlighting the susceptibilities and loop-holes within the components of security, various aspects of network that are not secured and also implementation of the intrusion-detection and prevention-system techniques are also described here. In this paper, proposed methods based on Neural Network is described that provides better way of attack detection, that are required in various applications of security such as network forensics, portable computer and the event handling systems by applying various different approaches. Proposed work is implemented in MATALB.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Downloads

Published

04/29/2016

How to Cite

Patil, K., Gour, D. B., & Tomar, M. D. (2016). A HYBRID APPROACH OF INTRUSION DETECTION SYSTEM BASED ON NEURAL NETWORK AND NORMALIZATION. SMART MOVES JOURNAL IJOSCIENCE, 2(2). https://doi.org/10.24113/ijoscience.v2i2.76