<![CDATA[Cybersecurity is a critical component of national defense, yet conventional Intrusion Detection Systems (IDS) often face limitations such as high false positive rates, detection delays, and difficulty adapting to dynamic attack patterns, leading to potential blind spots in defense networks. This study aims to design an adaptive IDS that balances detection accuracy, false positives, and operational efficiency through the application of multi objective Particle Swarm Optimization (PSO). Using the CICIDS2017 dataset, which simulates realistic modern network traffic and attack scenarios, we developed and evaluated a PSO optimized IDS model. The experimental methodology included preprocessing, feature selection, model training, and optimization of key performance objectives—maximizing detection rate (DR), minimizing false positive rate (FPR), and reducing latency. The results demonstrate that the proposed PSO IDS achieved a detection rate of 0.96 compared to 0.85 in conventional IDS, reduced the false positive rate from 0.18 to 0.07, and lowered average detection latency from 0.35 seconds to 0.12 seconds. Pareto front analysis confirmed that the multi objective optimization effectively balances conflicting parameters, delivering more robust and resilient intrusion detection. These findings indicate that PSO based multi objective IDS can serve as a practical and scalable solution for strengthening national cyber defense infrastructures, while also providing policy relevant insights on the integration of AI driven optimization methods into defense strategies.]]>
