Using Blockchain Technologies to Improve Security in Federated Learning Systems
- 1 July 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1183-1188
Abstract
The potential of Federated Learning (FL) deployment increases rapidly as the number of connected devices increases, the value of artificial intelligence is recognized and networking technologies and edge computing evolves. However, as in any distributed system, a set of security issues arise in FL systems. In this paper, we discuss the use of blockchain technology to address diverse security aspects of FL systems and focus on the model poisoning attack for which we propose a novel Blockchain-based defense scheme. An assessment using data from the MNIST database has shown that the proposed approach, which has been designed to be implemented on blockchain technology, offers significant protection against adversaries attempting model poisoning attacks. The approach adopts a novel algorithm for evaluating the model updates, by verifying each model update separately against a verification dataset, without requiring information about the training dataset size, which is often unavailable or easily falsified.Keywords
This publication has 14 references indexed in Scilit:
- Blockchained On-Device Federated LearningIEEE Communications Letters, 2019
- Blockchain analytics and artificial intelligenceIBM Journal of Research and Development, 2019
- Federated Machine LearningACM Transactions on Intelligent Systems and Technology, 2019
- A Pragmatic Introduction to Secure Multi-Party ComputationFoundations and Trends® in Privacy and Security, 2018
- Chained Anomaly Detection Models for Federated Learning: An Intrusion Detection Case StudyApplied Sciences, 2018
- Practical Secure Aggregation for Privacy-Preserving Machine Learning2017
- Calibrating Noise to Sensitivity in Private Data AnalysisJournal of Privacy and Confidentiality, 2017
- Deep Learning with Differential Privacy2016
- Large-Scale Machine Learning with Stochastic Gradient Descent2010
- Robust De-anonymization of Large Sparse Datasets2008 IEEE Symposium on Security and Privacy (SP 2008), 2008