Title: Machine learning-based security active defence model - security active defence technology in the communication network

Authors: Linjiang Xie; Feilu Hang; Wei Guo; Yao Lv; Wei Ou; C. Chandru Vignesh

Addresses: Yunnan Powergrid Co., Ltd., Kunming, Yunnan, China ' Yunnan Powergrid Co., Ltd., Kunming, Yunnan, China ' Yunnan Powergrid Co., Ltd., Kunming, Yunnan, China ' Yunnan Powergrid Co., Ltd., Kunming, Yunnan, China ' Yunnan Powergrid Co., Ltd., Kunming, Yunnan, China ' Department of Computer Science, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Avadi, Chennai, Tamil Nadu, India

Abstract: Nowadays, there is anticipated exponential growth in the number of internet-enabled devices, which will increase cyber threats across an expanding attack surface area. For guaranteeing network security, this study proposes the Machine Learning-based Security Active Defence Model (MLSADM). Machine Learning (ML) is how artificial intelligence learns patterns that lead to abnormal behaviour. This occurs when an artificial intelligence system or neural network is deceived into imperfectly recognising or intentionally adapting the input. An emerging type of attack and a coordinated attack is measured in the attack and defence situation. Experiments have been carried out with the dynamic (learning) attacker of a static (fixed) defender, static attackers and active attackers. The findings show that the proposed model enhances network security with high accuracy in network abnormal behaviour detection compared to other popular methods.

Keywords: communication network; security active defence technology; machine learning; network security.

DOI: 10.1504/IJIPT.2022.125955

International Journal of Internet Protocol Technology, 2022 Vol.15 No.3/4, pp.169 - 181

Received: 26 Dec 2020
Accepted: 01 May 2021
Published online: 05 Oct 2022 *

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