Binary Chaotic Gray Wolf Optimizer-Based Feature Selection for Intrusion Detection: A Comprehensive Study and Performance Evaluation

The importance of Intrusion Detection Systems (IDS), also known as intrusion prevention systems, rests in the fact that they protect the security and integrity of computer networks. They accomplish this essential mission by effectively detecting and neutralizing potential dangers. Researchers have begun turning to optimization algorithms to improve the accuracy and efficacy of IDS in response to cyberattacks’ ever-increasing sophistication and complexity. This research paper details how the Binary Chaotic Gray Wolf Optimizer (MGWO) can be used to find intrusions. The MGWO algorithm combines the best parts of the Gray Wolf Optimizer (GWO) and chaotic maps to make IDS work better overall and improve the feature selection process. The MGWO algorithm, its integration with intrusion detection, and its impact on system performance are dissected in great detail in this article. A performance comparison test is done to see how well MGWO works compared to other cutting-edge optimization methods often used in IDS.