FedVal: Different good or different bad in federated learning

TL;DR

FedVal is a novel federated learning approach that enhances robustness against poisoning attacks and reduces group bias without compromising privacy, achieving state-of-the-art results on multiple datasets.

Contribution

The paper introduces FedVal, a privacy-preserving server-side validation method that improves robustness and fairness in federated learning without requiring additional client data.

Findings

Robust against 80% malicious clients

Increases accuracy for underrepresented labels from 32% to 53%

Boosts recall for underrepresented features from 19% to 50%

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%.