Title: Detection of Botnet using deep learning algorithm: application of machine learning in cyber-security

Authors: A. Sivakumar; J. Jency Rubia; Hima Vijayan; C. Sivakumaran

Addresses: Department of Data Science and Business Systems, SRM Institute of Science and Technology, SRM Nagar, Kattankulathur, Tamil Nadu, India ' Department of Electronics and Communication Engineering, K. Ramakrishnan College of Engineering, Trichy, Tamil Nadu, India ' Department of Information Technology, SA Engineering College, Chennai, India ' Photon Technologies, Chennai, 600017, India

Abstract: Machine learning has been made possible as a result of the availability and accessibility of a massive amount of data gathered by internet-connected sensors. The concept of machine learning exhibits and spreads the notion that a computer has the potential to develop itself over the course of time. We investigate a variety of security applications from a variety of angles in which ML models play a key role, and we compare the accuracy outcomes of these models using a variety of conceivable dimensions. To provide an accurate depiction of the qualities associated with security, we have shown the threat model and defence strategies against adversarial attack techniques. The proposed method shows about 88% accuracy for the used data. These attacks are based on the fact that the adversaries are aware of the model.

Keywords: adversarial attack; security; machine learning; deep learning; LSTM.

DOI: 10.1504/IJESDF.2024.137030

International Journal of Electronic Security and Digital Forensics, 2024 Vol.16 No.2, pp.213 - 222

Received: 30 Sep 2022
Accepted: 06 Dec 2022
Published online: 01 Mar 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article