A comprehence study of DDoS attack detecting algorithm using GRU-BWFA classifier

The suggested classifier, Gated Recurrent Unit Neural Network, is utilised to produce the appropriate classification in this research. It is based on Bidirectional weighted feature averaging (GRU-BWFA). The findings show that each classifier performs differently, with the accuracy rate ranging betwe...

Full description

Saved in:
Bibliographic Details
Published in:Measurement. Sensors 2022-12, Vol.24, p.100570, Article 100570
Main Authors: Gangula, Rekha, Mohan, V. Murali, Kumar, Ranjeeth
Format: Article
Language:English
Subjects:
Attack
Classification
DDoS
Deep learning
GRU-BWFA
Recurrent neural network
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The suggested classifier, Gated Recurrent Unit Neural Network, is utilised to produce the appropriate classification in this research. It is based on Bidirectional weighted feature averaging (GRU-BWFA). The findings show that each classifier performs differently, with the accuracy rate ranging between the three. GRU-BWFA, the suggested system, has the greatest accuracy rate of 99.9%. The suggested approach outperformed current algorithms to categorise and identify several attacks from the SNMP-MIB dataset, including TCP-SYN, UDP flood, ICMP-echo, HTTP flood, Slow Loris, Slow Post, and Brute force, with a detection rate of 99.9%. As a result, the System is effectively restored in the shortest possible time.
ISSN:2665-9174
2665-9174
DOI:10.1016/j.measen.2022.100570