چکيده
The Internet of Things (IoT) and its expanding network of interconnected devices have heightened the demand for efficient and secure communication, especially in resource-constrained environments. The IETF’s Routing Over Low power and Lossy network (ROLL) working group developed the IPv6 Routing Protocol for Low Power and Lossy Networks (RPL) to enable efficient routing within 6LoWPAN networks. However, the limited resources of 6LoWPAN nodes create challenges in maintaining robust security, leaving these networks vulnerable to various threats. Recent advancements in Machine Learning (ML) and Deep Learning (DL) have shown promise in detecting anomalies within RPL-based networks. This report systematically reviews the current research landscape on ML and DL methods, as well as combined approaches, for securing RPL-based 6LoWPAN environments. Through a rigorous analysis of 15,543 studies from major databases (Google Scholar, Springer Link, Scopus, Science Direct, and IEEE Xplore®) and refined by inclusion criteria, 49 relevant studies from 2016 to 2021 were selected. The review examines these studies’ methodologies, datasets, and identified gaps, offering a critical analysis of current detection techniques. The findings emphasize persistent challenges and highlight future research directions, aiming to bolster RPL’s security and ensure resilient IoT networks in vulnerable, resource-limited contexts.
