INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
open access , Peer-reviewed, and Refereed Journals, Impact factor 8.15
Implementation and Comparison of various ML and Deep Learning Techniques for Network Intrusion Detection System
Authors Name:
Shreevatsa T P
, Radhika K R
Unique Id:
IJSDR2209133
Published In:
Volume 7 Issue 9, September-2022
Abstract:
With the advent of internet to almost every walk of contemporary life, the need for internet security is ever increasing. The threat to the system can be a Denial-of-Service attack or a Worm attack or a Fuzzers attack and causing the integrity of the system to collapse or to compromise. Thus, to monitor the system network, Intrusion Detection System are extensively used in the cybersecurity domain. In order to detect attacks and subsequently thwart such future attacks, the project uses Machine Learning and Deep Learning algorithms to find and detect such attacks. The project is built on UNSW-NB15 (modern substitute to the well-known KDD99 Dataset) to analyze and classify normal and abnormal packets. The paper also sheds some light on few Machine Learning and Deep Learning Algorithms and makes a comparative study on them.
Keywords:
Machine Learning Algorithms, Deep Learning, Intrusion Detection System
Cite Article:
"Implementation and Comparison of various ML and Deep Learning Techniques for Network Intrusion Detection System", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.7, Issue 9, page no.833 - 838, September-2022, Available :http://www.ijsdr.org/papers/IJSDR2209133.pdf
Downloads:
000337074
Publication Details:
Published Paper ID: IJSDR2209133
Registration ID:201529
Published In: Volume 7 Issue 9, September-2022
DOI (Digital Object Identifier):
Page No: 833 - 838
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn