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
A Multiclass Approach for Network Intrusion Detection using Convolutional Neural Networks
Authors Name:
Shashank Shekhar
, Abhinav Mittra
Unique Id:
IJSDR2004044
Published In:
Volume 5 Issue 4, April-2020
Abstract:
The immense popularity of Internet of Things (IoT) and Cloud based applications have resulted in huge volumes of network traffic. Different versions of operating systems, multiple protocols and concurrent users contribute significantly towards the ever increasing computer security threats. Traditional methods involving shallow learning tech- niques like Random Forest, Naive Bayes, etc. have been instrumental in advancing the study of network intrusion detection. However, as and when the network data expands in size and complexity, deep learning algorithms are required to tackle the ongoing network security challenges. Deep learning methods are intrinsically capable of handling enormous data and their performance increases with increasing supply of the same. The proposed work details the configuration of a multi-class classifier using Convolutional Neural Networks. UNSW NB-15, a modern dataset comprising of nine contemporary attack types is used to evaluate the effectiveness of the proposed approach. Results indicate that the proposed approach has exhibited a reasonably valid precision and recall percentage as compared to the preexisting methods.
"A Multiclass Approach for Network Intrusion Detection using Convolutional Neural Networks", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.5, Issue 4, page no.253 - 262, April-2020, Available :http://www.ijsdr.org/papers/IJSDR2004044.pdf
Downloads:
000337211
Publication Details:
Published Paper ID: IJSDR2004044
Registration ID:191637
Published In: Volume 5 Issue 4, April-2020
DOI (Digital Object Identifier): http://doi.one/10.1729/Journal.23883
Page No: 253 - 262
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn