Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195194,
        author = {BHAGYA LAKSHMI C and Dr. M. VARGHEESE},
        title = {OPTIMIZING CYBERSECURITY THREAT DETECTION: AN INTEGRATED APPROACH USING PARTICLE SWARM OPTIMIZATION AND GENERATIVE ADVERSARIAL NETWORKS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {6790-6815},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195194},
        abstract = {This project presents an innovative security framework for Mobile Ad hoc Networks (MANETs), utilizing a Particle Swarm Optimization (PSO) algorithm combined with a Generative Adversarial Network (GAN) to improve the performance of Intrusion Detection Systems (IDS). Due to their dynamic and decentralized nature, MANETs are highly vulnerable to a range of security threats, including unauthorized data access, routing attacks, and denial-of-service attacks. To mitigate these risks, the proposed framework employs PSO, a bio-inspired optimization algorithm that mimics the social behavior of bird flocking and fish schooling. PSO is used to enhance the feature selection process, ensuring that the most relevant features for intrusion detection are identified and prioritized through global best optimization. The second component, GAN, incorporates deep learning techniques with supervised classification to accurately identify and classify network intrusions based on the selected features. By training on labeled datasets such as NSL-KDD, UNSW-NB15, and D820S, GAN effectively distinguishes between normal and malicious traffic, ensuring reliable detection. The combination of PSO and GAN not only strengthens the feature extraction and selection process but also improves the overall detection capability. This hybrid approach is highly adaptable, capable of handling the evolving and complex nature of attacks in MANETs. Experimental results demonstrate the framework’s superior performance in terms of detection accuracy, false alarm rates, and computational efficiency, providing a robust solution for addressing the security challenges inherent in MANET environments. This project is implemented using NS-2 simulation.},
        keywords = {},
        month = {March},
        }