Detection of Global Anomalies on Distributed IoT Edges with Device-to-Device Communication

TL;DR

This paper introduces a fully distributed federated learning scheme called WAFL-Autoencoder for detecting global anomalies across multiple IoT devices using device-to-device communication, achieving high accuracy and low false positives.

Contribution

The paper proposes a novel distributed anomaly detection method using Wireless Ad Hoc Federated Learning for IoT devices, focusing on global anomalies and collaborative threshold finding.

Findings

High true positive rates in anomaly detection

Low false positive rates achieved

Effective collaborative threshold determination

Abstract

Anomaly detection is an important function in IoT applications for finding outliers caused by abnormal events. Anomaly detection sometimes comes with high-frequency data sampling which should be carried out at Edge devices rather than Cloud. In this paper, we consider the case that multiple IoT devices are installed in a single remote site and that they collaboratively detect anomalies from the observations with device-to-device communications. For this, we propose a fully distributed collaborative scheme for training distributed anomaly detectors with Wireless Ad Hoc Federated Learning, namely "WAFL-Autoencoder". We introduce the concept of Global Anomaly which sample is not only rare to the local device but rare to all the devices in the target domain. We also propose a distributed threshold-finding algorithm for Global Anomaly detection. With our standard benchmark-based evaluation, we have confirmed that our scheme trained anomaly detectors perfectly across the devices. We have also confirmed that the devices collaboratively found thresholds for Global Anomaly detection with low false positive rates while achieving high true positive rates with few exceptions.