Abstract: This review paper explores the current advancements in intrusion detection and anomaly detection systems specifically designed for Internet of Things (IoT) environments, focusing on the integration of machine learning techniques. As IoT devices proliferate, so do the associated security vulnerabilities, necessitating robust detection mechanisms to safeguard sensitive data and maintain system integrity. The paper synthesizes findings from various studies, highlighting the efficacy of hybrid models, supervised and unsupervised learning algorithms, and their applications in addressing diverse security challenges. Key outcomes demonstrate significant improvements in detection accuracy and efficiency; however, challenges such as adaptability to evolving threats, scalability, and real-world deployment persist. The review underscores the need for adaptive algorithms, federated learning approaches, and lightweight solutions tailored for resource-constrained devices. Furthermore, it emphasizes the importance of collaboration across sectors to drive research forward. Ultimately, this paper aims to provide insights into future research directions that can enhance the security landscape of IoT systems, contributing to the development of more resilient cybersecurity frameworks.
Keywords: Internet of Things (IoT), Intrusion Detection Systems (IDS), Anomaly Detection, Cybersecurity, Real-time Monitoring, Adaptive Algorithms, Federated Learning, Data Privacy.
|
DOI:
10.17148/IJARCCE.2024.131009
