Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design

Chuan Ma, Jun Li, Ming Ding, Kang Wei, Wen Chen, H. Vincent Poor

Research output: Contribution to journalArticlepeer-review

17 Scopus citations


Owing to the low communication costs and privacy-promoting capabilities, federated learning (FL) has become a promising tool for training effective machine learning models among distributed clients. However, with the distributed architecture, low-quality models could be uploaded to the aggregator server by unreliable clients, leading to a degradation or even a collapse of training. In this article, we model these unreliable behaviors of clients and propose a defensive mechanism to mitigate such a security risk. Specifically, we first investigate the impact on the models caused by unreliable clients by deriving a convergence upper bound on the loss function based on the gradient descent updates. Our bounds reveal that with a fixed amount of total computational resources, there exists an optimal number of local training iterations in terms of convergence performance. We further design a novel defensive mechanism, named deep neural network-based secure aggregation (DeepSA). Our experimental results validate our theoretical analysis. In addition, the effectiveness of DeepSA is verified by comparing with other state-of-the-art defensive mechanisms.

Original languageEnglish (US)
Pages (from-to)17308-17319
Number of pages12
JournalIEEE Internet of Things Journal
Issue number24
StatePublished - Dec 15 2021
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications


  • Convergence bound
  • defensive mechanism
  • federated learning (FL)
  • unreliable clients


Dive into the research topics of 'Federated Learning with Unreliable Clients: Performance Analysis and Mechanism Design'. Together they form a unique fingerprint.

Cite this