FedClamp: an Algorithm for Identification of Anomalous Client in Federated Learning

Manzoor, H. U., Khan, M. S., Khan, A. R., Ayaz, F., Flynn, D. , Imran, M. A. and Zoha, A. (2022) FedClamp: an Algorithm for Identification of Anomalous Client in Federated Learning. In: ICECS 2022: 29th IEEE International Conference on Electronics, Circuits & Systems, Glasgow, UK, 24-26 October 2022, ISBN 9781665488235 (doi: 10.1109/ICECS202256217.2022.9970909)

Abstract

With the ever-increasing internet of things (IoT) and the rise of edge computing, federated learning (FL) is considered a promising solution for privacy and latency-aware applications. However, the data is highly distributed among several clients, making it challenging to monitor node anomalies caused by malfunctioning devices or any other unforeseen reasons. In this paper, we propose FedClamp, an anomaly detection algorithm based on the hidden Markov model (HMM) in the FL environment. FedClamp identifies the anomalous node and isolates them before aggregation to improve the performance of the global model. FedClamp was tested in a short-term energy forecasting problem using artificial neural networks when the FL environment had five clients. The algorithm uses mean absolute percentage error (MAPE) generated from local models and clusters them in normal and faulted nodes using HMM. The anomalous nodes identified using this algorithm are isolated before aggregation and achieve global model convergence with few communication rounds.

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Zoha, Dr Ahmed and Khan, Ahsan Raza and Manzoor, Habib Ullah and Imran, Professor Muhammad and Flynn, Professor David and Ayaz, Fahad
• Authors: Manzoor, H. U., Khan, M. S., Khan, A. R., Ayaz, F., Flynn, D., Imran, M. A., and Zoha, A.
• College/School: College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity; College of Science and Engineering > School of Engineering > Systems Power and Energy
• ISBN: 9781665488235
• Copyright Holders: Copyright © 2022 IEEE
• First Published: First published in 2022 29th IEEE International Conference on Electronics, Circuits and Systems (ICECS)
• Publisher Policy: Reproduced in accordance with the publisher copyright policy