Federated Isolation Forest for Efficient Anomaly Detection on Edge IoT Systems

2025-06-05

AI Summary

To address the challenge of anomaly detection on resource-constrained and privacy-sensitive edge IoT devices, this paper proposes a lightweight federated learning framework based on Isolation Forest—the first to adapt and deploy Isolation Forest in MicroPython-enabled embedded environments. The method employs unsupervised distributed modeling, eliminating raw data transmission to preserve end-device privacy. Through model pruning and inference optimization, memory overhead is significantly reduced. Experimental results demonstrate that the framework achieves over 78% anomaly detection accuracy and greater than 96% classification accuracy across heterogeneous device configurations, while maintaining training memory consumption below 160 KB. It enables real-time, continuous collaborative learning on ultra-low-power edge devices. This work establishes a viable technical pathway for privacy-preserving edge intelligence, bridging the gap between robust unsupervised anomaly detection and practical deployment constraints in embedded federated systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Recently, federated learning frameworks such as Python TestBed for Federated Learning Algorithms and MicroPython TestBed for Federated Learning Algorithms have emerged to tackle user privacy concerns and efficiency in embedded systems. Even more recently, an efficient federated anomaly detection algorithm, FLiForest, based on Isolation Forests has been developed, offering a low-resource, unsupervised method well-suited for edge deployment and continuous learning. In this paper, we present an application of Isolation Forest-based temperature anomaly detection, developed using the previously mentioned federated learning frameworks, aimed at small edge devices and IoT systems running MicroPython. The system has been experimentally evaluated, achieving over 96% accuracy in distinguishing normal from abnormal readings and above 78% precision in detecting anomalies across all tested configurations, while maintaining a memory usage below 160 KB during model training. These results highlight its suitability for resource-constrained environments and edge systems, while upholding federated learning principles of data privacy and collaborative learning.

Problem

• Develop federated anomaly detection for edge IoT systems
• Ensure low-resource unsupervised learning on small devices
• Maintain high accuracy and privacy in federated learning

Innovation

• Federated Isolation Forest for anomaly detection
• Low-resource unsupervised edge deployment
• MicroPython-based privacy-preserving collaborative learning