Hybrid Deep Learning for Botnet Attack Detection

Muniyasamy V , Mr.Ganesh kumar S , Manicka Mathavan M , Vijayaprabakar V

Botnet Iot Attack, LSTM, CNN, Auto encoder

Deep Learning is an efficient method for the botnet attack detection. Usually the volume of network traffic data and its required large memory space. Principal Component Analysis is one of the common linear methods like kernel methods, DL and Spectral methods employ non-linear transformation techniques. It is impossible to implement the DL method in memory constrained IOT devices. We reduce the large-scale IOT network traffic data using to reduction techniques. Bot dataset is the most common dataset that is publicly available for the network-based botnet attack detection. These traffic attack samples can be categorized into four botnet scenarios namely: DOS, DDOS, Information theft and Reconnaissance. Auto Encoder is an unsupervised method that produces lack of space representation of input data at the hidden layer. Different auto encoder architectures have been used to reduce the feature dimensionally in most popular intrusion datasets. We have to avoid the long short-term memory and to implement the convolutional Neural Network. Finally, the results show that the performance like more accuracy.

Published Paper   E-Certificate

"Hybrid Deep Learning for Botnet Attack Detection ", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.7, Issue 6, page no.273 - 278, June-2022, Available :https://ijsdr.org/papers/IJSDR2206044.pdf

Volume 7 Issue 6, June-2022

Pages : 273 - 278

Paper Reg. ID: IJSDR_200558

Published Paper Id: IJSDR2206044

Downloads: 000347228

Research Area: Computer Engineering 

Country: Kurunthamadam/Virudhunagar district., Tamil nadu, India

Published Paper PDF: https://ijsdr.org/papers/IJSDR2206044

Published Paper URL: https://ijsdr.org/viewpaperforall?paper=IJSDR2206044

ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016

An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator

Publisher: IJSDR(IJ Publication) Janvi Wave

This work is licensed under a Creative Commons Attribution 4.0 International License and The Open Definition