Sustainable Security Solutions for IoT: Enhancing Intrusion Detection Using AI and Machine Learning
Inaya Imtiyaz Khan, Yadidiah Kanaparthi, Yash Ruchandani, Aliya Rizwan · 2024
The rapid expansion of the Internet of Things (IoT) has significantly increased the complexity and vulnerability of interconnected systems, posing a challenge to sustainable cybersecurity. With an emphasis on sustainable security practices, this article offers a thorough analysis of machine learning (ML) and artificial intelligence (AI) approaches for intrusion detection systems (IDS) in Internet of Things (IoT) contexts. We examine various AI-ML-based IDS approaches, emphasizing resource-efficient algorithms, energy-saving data processing techniques, and scalable solutions for real-time anomaly detection. Our review includes a comparison of methods based on criteria such as processing efficiency, energy consumption, and integration with existing sustainable practices in IoT ecosystems. The paper highlights the potential of AI-ML techniques to not only improve intrusion detection accuracy but also enhance the sustainability of IoT security through optimized computational resources and eco-friendly approaches. We identify current research gaps and suggest future directions for developing sustainable IDS solutions, including lightweight hybrid classifiers and privacy-preserving techniques that minimize data transfer.