Fairfed: Cross-device fair federated learning

Muhammad Habib Ur Rehman, Ahmed Mukhtar Dirir, Khaled Salah, Davor Svetinovic

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations


Federated learning (FL) is the rapidly developing machine learning technique that is used to perform collaborative model training over decentralized datasets. FL enables privacy-preserving model development whereby the datasets are scattered over a large set of data producers (i.e., devices and/or systems). These data producers train the learning models, encapsulate the model updates with differential privacy techniques, and share them to centralized systems for global aggregation. However, these centralized models are always prone to adversarial attacks (such as data-poisoning and model poisoning attacks) due to a large number of data producers. Hence, FL methods need to ensure fairness and high-quality model availability across all the participants in the underlying AI systems. In this paper, we propose a novel FL framework, called FairFed, to meet fairness and high-quality data requirements. The FairFed provides a fairness mechanism to detect adversaries across the devices and datasets in the FL network and reject their model updates. We use a Python-simulated FL framework to enable large-scale training over MNIST dataset. We simulate a cross-device model training settings to detect adversaries in the training network. We used TensorFlow Federated and Python to implement the fairness protocol, the deep neural network, and the outlier detection algorithm. We thoroughly test the proposed FairFed framework with random and uniform data distributions across the training network and compare our initial results with the baseline fairness scheme. Our proposed work shows promising results in terms of model accuracy and loss.

Original languageBritish English
Title of host publication2020 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728182438
StatePublished - 13 Oct 2020
Event2020 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2020 - Washington, United States
Duration: 13 Oct 202015 Oct 2020

Publication series

NameProceedings - Applied Imagery Pattern Recognition Workshop
ISSN (Print)2164-2516


Conference2020 IEEE Applied Imagery Pattern Recognition Workshop, AIPR 2020
Country/TerritoryUnited States


  • Data Quality
  • Deep Learning
  • Fairness
  • Federated Learning
  • Model Development
  • Outlier Detection


Dive into the research topics of 'Fairfed: Cross-device fair federated learning'. Together they form a unique fingerprint.

Cite this