Machine Learning‐Based Malicious Threat Detection and Security Analysis on Software‐Defined Networking for Industry 4.0
J. Ramprasath, Navin Kumar, N. Krishnaraj, M. Gomathi · 2023
Traditional data communication networking is not suitable for industry 4.0. So industry moves to implement software-defined networks for managing the networks. But security is an important thread in a software-defined network. Most attackers are easily getting access to the resource in the industry. The Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks cause heavy damage in the production area. Malicious attacks will create a services gap; network services throughput enter into a down state, and there is a loss in business continuity. Traditional Intrusion Detection System (IDS) will detect malicious traffic based on a predefined access control list but it cannot detect new malicious traffic ingress into home networks. Machine learning techniques will lead to better identification of threats to synthetic or real-time data. To avoid these situations, we are proposing a model to find the attackers in the network and train the model to find the new type of intruder in the system.