Abstract
Federated learning is the new tide that is being associated with machine learning territory. It is an attempt to enable smart edge devices to confederate a mutual prediction model while the training data is residing at the respective edge device. This facilitates our data to be more secure, use less bandwidth, lower latency, and power consumption. We exercise the concept of federated learning in our neural network autoencoder model to detect the anomaly. Anomaly detection is finding the unusual pattern in a given data stream which may be a false or mal-entry in the pool of transactions. It helps us to prevent many online theft and scams which are detected using state-of-the-art machine learning and deep learning algorithms. All this has to be implemented in smart edge devices that have enough computing power to train the models provided to them.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
H.B. McMahan, E. Moore, D. Ramage, S. Hampson, B. Aguera y Arcas, Communication-Efficient Learning on Deep Networks from Decentralized Data (AISTATS, 2017)
V. Chandola, A. Banerjee, V. Kumar, Anomaly detection: a survey. ACM Comput. Surv. 41(3), 6 (2009)
M. Martinelli, E. Tronci, G. Dipoppa, C. Balducelli, Electric power systems anomaly detection using neural networks, in International Conference on Knowledge-Based and Intelligent Information and Engineering Systems (2014)
H. Ullah, M. Ullah, N. Conci, Real-time anomaly detection in dense crowded scenes, in Video Surveillance and Transportation Imaging Applications (2014)
A. Dau, V. Ciesielski, A. Song, Anomaly detection using replicator neural networks trained on examples of one class, in SEAL (2014)
C. David et al., A practical tutorial on autoencoders for nonlinear feature fusion: taxonomy, models, software and guidelines. Inf. Fusion 44, 78–96 (2018)
Y. LeCun, Y. Bengio, G. Hinton, Deep learning. Nature (2015)
G. Markus, “kdd99-unsupervised-ad.tab”, Unsupervised Anomaly Detection Benchmark (2015). https://doi.org/10.7910/DVN/OPQMVF/GIPF3O, Harvard Dataverse, V1, UNF:6:WwXF9CrMJIdTvBZfZ4vpyg==[fileUNF]
G. Markus, “shuttle-unsupervised-ad.tab”, Unsupervised Anomaly Detection Benchmark (2015). https://doi.org/10.7910/DVN/OPQMVF/VW8RDW, Harvard Dataverse, V1, UNF:6:sQatmd5Ao0CdXQULYgoDqQ==[fileUNF]
J. Schneible, A. Lu, Anomaly detection on the edge, in MILCOM 2017–2017 IEEE Military Communications Conference (MILCOM) (IEEE, 2017)
G. Markus, Unsupervised Anomaly Detection Benchmark. https://doi.org/10.7910/DVN/OPQMVF, Harvard Dataverse, V1, UNF:6:EnytiA6wCIilzHetzQQV7A==[fileUNF]
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Singh, S., Bhardwaj, S., Pandey, H., Beniwal, G. (2021). Anomaly Detection Using Federated Learning. In: Bansal, P., Tushir, M., Balas, V., Srivastava, R. (eds) Proceedings of International Conference on Artificial Intelligence and Applications. Advances in Intelligent Systems and Computing, vol 1164. Springer, Singapore. https://doi.org/10.1007/978-981-15-4992-2_14
Download citation
DOI: https://doi.org/10.1007/978-981-15-4992-2_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-4991-5
Online ISBN: 978-981-15-4992-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)