Dynamic Anomaly Detection Using Robust Random Cut Forests in Resource-Constrained IoT Environments

This paper investigates dynamic anomaly detection in resource-constrained environments by leveraging Robust Random Cut Forests (RRCF). Anomaly detection is crucial for maintaining the integrity and security of data streams in Internet of Things (IoT) environments, where data is continuously generated and often subject to noise and fluctuations. We begin with a comprehensive exploration of resilient random cut data structures tailored for analyzing incoming data streams, highlighting their effectiveness in adapting to the dynamic nature of IoT. Our methodology encompasses extensive experimentation with diverse datasets, including real-time Arduino data and benchmark datasets such as 101-23 and CIC-IoT. Through this approach, we assess the performance of the RRCF algorithm under various scenarios, focusing on its capability to accurately identify trends and anomalies over time. Notably, we achieve significant performance improvements, with an average Area Under the Curve (AUC) of 95.6 and an FI score of 0.86, demonstrating RRCF's $ effectiveness in real-time anomaly detection. To further enhance detection accuracy, we introduce dynamic thresholds that adapt to changing data characteristics, allowing our model to maintain robust performance even in the presence of noise. Detailed evaluations reveal that our approach consistently outperforms existing state-of-the-art methods, particularly in terms of handling noisy data and ensuring computational efficiency under resource constraints. The findings underscore the potential of ККСЕ as a powerful tool for real-time applications within IoT systems, providing a solid theoretical foundation for future advancements in dynamic anomaly detection. By investigating non-parametric anomalies and analyzing the influence of external factors on data integrity, we uncover hidden patterns amidst dynamic fluctuations. This research emphasizes the need for adaptive strategies in evolving data landscapes, laying the groundwork for enhanced resilience and accuracy in anomaly detection methodologies. In summary, this study presents a novel approach that integrates theoretical insights, updating strategies, and empirical experimentation, making a valuable contribution to the field of anomaly detection in resourceconstrained environments. The implications of our work extend beyond theoretical foundations, offering practical solutions for real-time monitoring and anomaly detection in complex, dynamic systems.