Skip to content
CaMLSysUniversity of Cambridge
Home People Publications Projects Contact

← All publications

FedVal: Different good or different bad in federated learning

  • Viktor ValadiAI Sweden
  • Xinchi QiuUniversity of Cambridge
  • Pedro Porto Buarque de GusmãoUniversity of Cambridge
  • Nicholas D. LaneUniversity of Cambridge
  • Mina AlibeigiUniversity of CambridgeZenseact

USENIX Security Symposium, 2023

Abstract

Federated learning (FL) systems are susceptible to attacks from malicious actors who might attempt to corrupt the training model through various poisoning attacks. FL also poses new challenges in addressing group bias, such as ensuring fair performance for different demographic groups. Traditional methods used to address such biases require centralized access to the data, which FL systems do not have. In this paper, we present a novel approach FedVal for both robustness and fairness that does not require any additional information from clients that could raise privacy concerns and consequently compromise the integrity of the FL system. To this end, we propose an innovative score function based on a server-side validation method that assesses client updates and determines the optimal aggregation balance between locally-trained models. Our research shows that this approach not only provides solid protection against poisoning attacks but can also be used to reduce group bias and subsequently promote fairness while maintaining the system’s capability for differential privacy. Extensive experiments on the CIFAR-10, FEMNIST, and PUMS ACSIncome datasets in different configurations demonstrate the effectiveness of our method, resulting in state-of-the-art performances. We have proven robustness in situations where 80% of participating clients are malicious. Additionally, we have shown a significant increase in accuracy for underrepresented labels from 32% to 53%, and increase in recall rate for underrepresented features from 19% to 50%.

Materials

  • PDF
BibTeX
@inproceedings{viktor2023fedval,
  title = {{FedVal: Different good or different bad in federated learning}},
  author = {Valadi, Viktor and Qiu, Xinchi and de Gusmão, Pedro Porto Buarque and Lane, Nicholas D. and Alibeigi, Mina},
  year = {2023},
  booktitle = {USENIX Security Symposium},
  pages = {6365--6380},
  publisher = {USENIX Association},
  url = {https://www.usenix.org/conference/usenixsecurity23/presentation/valadi}
}
Cambridge Machine Learning Systems Group
Department of Computer Science and Technology
University of Cambridge
ContactGitHub