Federated Anomaly Detection over Distributed Data Streams

TL;DR

This paper presents a novel federated learning framework for anomaly detection in distributed data streams, addressing privacy restrictions and enabling collaborative AI analysis across multiple data sources.

Contribution

It adapts data stream anomaly detection algorithms to a federated setting and demonstrates a practical, robust framework for real-world distributed deployment.

Findings

Effective anomaly detection in federated data streams.

Framework proven feasible in real-world deployment.

Addresses privacy concerns in distributed data analysis.

Abstract

Sharing of telecommunication network data, for example, even at high aggregation levels, is nowadays highly restricted due to privacy legislation and regulations and other important ethical concerns. It leads to scattering data across institutions, regions, and states, inhibiting the usage of AI methods that could otherwise take advantage of data at scale. It creates the need to build a platform to control such data, build models or perform calculations. In this work, we propose an approach to building the bridge among anomaly detection, federated learning, and data streams. The overarching goal of the work is to detect anomalies in a federated environment over distributed data streams. This work complements the state-of-the-art by adapting the data stream algorithms in a federated learning setting for anomaly detection and by delivering a robust framework and demonstrating the practical feasibility in a real-world distributed deployment scenario.