Preserving Security in Internet of Things Healthcare System with Metaheuristic Driven Intrusion Detection

Goswami N.; Raj S.; Thakral D.; Gonzáles J.L.A.; Albornoz J.F.; Salazar E.; Kapila D.; Yadav S.; Kumar S. · Engineered Science (2023) · DOI: 10.30919/es933

Resumen

The Internet of Things (IoT) makes IoT devices more vulnerable to cyberattacks, especially Distributed Denial of Service (DDoS), raising privacy and security issues. Application layer DDoS: zombie machines submit queries to the affected server. IDS cannot detect these requests because TCP connections are valid. In this research, we propose the Lion Salp Swarm Optimiz ation Algorithm (LSSOA), which utilizes the freely available IoT Flock software to create a dataset containing both legitimate and malicious traffic. We employ metaheuristic algorithms like Lion optimization, Whale optimization, Spider Monkey optimization, and Salp Swarm optimization to detect online attacks and defend the Internet of Medical Things (IoMT) environment. Our framework accurately detects attacks while reducing false positives by overcoming intrusion detection restrictions. Our metaheuristic al gorithm outperforms others. Our method is useful for Internet of Things based enterprises. Overall, the LSSOA framework provides a powerful tool to detect and prevent cyber attacks in the IoMT environment, demonstrating the potential benefits of novel intr usion detection techniques. Our study emphasizes the importance of enhancing IoT security, particularly in critical industries like healthcare, and highlights the need for continuous efforts t o develop effective and innovative approaches to address emergin g cyber threats.

Instituciones: Universidad Tecnológica de los Andes; Universidad Nacional Santiago Antúnez de Mayolo