Volume 18, No. 6, 2021
A Novel Approach To Intrusion Detection And Prevention In Computer Networks Using Control Systems
Dr. Thai Son Chu
Abstract
This research article explores a novel approach to enhancing Intrusion Detection and Prevention Systems (IDPS) by integrating control systems theory with machine learning techniques. Traditional IDPS often suffer from limitations such as high false positive rates, slow response times, and limited adaptability to evolving threats. To address these challenges, we propose a dynamic and adaptive IDPS framework that leverages control systems principles to continuously adjust detection parameters and machine learning models to improve accuracy and response times. The research methodology involves the development and evaluation of the proposed IDPS in both simulated and real-world environments. Key metrics including detection accuracy, false positive rates, response time, and resource efficiency are measured and compared against traditional and commercial IDPS solutions. The results demonstrate significant improvements in detection accuracy, with a true positive rate of 95% in simulations and 93% in real-world testing, along with reduced false positive rates of 5% and 6% respectively. Moreover, the proposed system exhibits faster response times and efficient resource utilization, making it suitable for deployment in various network environments.
Pages: 9775-9787
Keywords: Intrusion Detection and Prevention Systems, Control Systems Theory, Machine Learning, Dynamic Adjustment, Detection Accuracy, False Positive Rate, Response Time, Resource Efficiency.