| Sumario: | Organizational resilience faces an increasing worldwide threat from ransomware attacks, which disrupt essential infrastructure and result in major financial and operational damage. The incidents create extended system outages, which trigger a chain reaction of disruptions throughout supply chains and connected systems. This research develops a genetic algorithm (GA)-based solution to optimize disaster recovery operations after ransomware attacks occur. The model works to achieve three major objectives, which include minimizing recovery time objective (RTO) and restoring vital systems first while optimizing resource distribution within financial limits. The GA uses selection, crossover, and mutation to develop recovery sequences through an iterative process of multiobjective optimization. The simulation analyzed eight enterprise systems, which had different criticality levels and cost and availability characteristics. Simulation results show that the GA-optimized recovery plan performs better than standard and random recovery approaches by cutting down RTO and recovery expenses while enhancing system operational availability. The research demonstrates how evolutionary computing enhances cyber risk management while providing a flexible framework to boost ransomware resistance in advanced digital systems.
|
|---|