Evolving Security: Leveraging Genetic Mutation Algorithms for Cyber Threat Prevention and Mitigation

Abstract

Research specifically on using genetic mutation algorithms to detect, mitigate and prevent cyberattacks is rare, although many research papers can be found on genetic algorithms on detection and identification, but not on mitigation or prevention. This research sought to address this gap. The objectives were to evaluate the status of genetic mutation algorithms for the mitigation and prevention of cyberattacks, to design and develop a genetic mutation algorithm to mitigate and prevent cyberattacks and to validate the developed algorithm by comparing the best performance of this and other algorithms developed for the same purposes. The status based on current research has already been stated above. A genetic mutation algorithm was developed using Simulation Environment and Algorithm Development (including mutation operators, fitness function and selection process in the algorithm) and threat detection rate, false positive rate, response time and system performance for evaluation. The proposed model was benchmarked against conventional signature-based and heuristic-based cybersecurity solutions. Data logs from simulated attacks were analysed using pseudocodes to compare performance across different methodologies. The results showed that genetic mutation algorithm had a superior adaptability to novel threats, reducing the impact of zero-day vulnerabilities. Also, traditional security systems struggled with emerging threats, whereas the evolutionary nature of the genetic mutation model continuously improved detection and response capabilities.