Federated Anomaly Detection over Distributed Data Streams
This work addresses privacy-preserving anomaly detection for telecommunication networks, but it is incremental as it adapts existing methods to a federated setting.
The authors tackled the problem of detecting anomalies in distributed data streams under privacy constraints by adapting data stream algorithms in a federated learning setting, resulting in a robust framework demonstrated as practically feasible in real-world deployment.
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.