# PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning

Source: [PUFFLE: Balancing Privacy, Utility, and Fairness in Federated Learning](<https://www.sota2.com/research/paper/68fa742d1e209131cea603b9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:36:01.943Z

Authors: Luca Corbucci, Mikko A Heikkila, David Solans Noguero, Anna Monreale, Nicolas Kourtellis

Published: 2024-07-21T17:22:18.000Z

## Abstract

Training and deploying Machine Learning models that simultaneously adhere to principles of fairness and privacy while ensuring good utility poses a significant challenge. The interplay between these three factors of trustworthiness is frequently underestimated and remains insufficiently explored. Consequently, many efforts focus on ensuring only two of these factors, neglecting one in the process. The decentralization of the datasets and the variations in distributions among the clients exacerbate the complexity of achieving this ethical trade-off in the context of Federated Learning (FL). For the first time in FL literature, we address these three factors of trustworthiness. We introduce PUFFLE, a high-level parameterised approach that can help in the exploration of the balance between utility, privacy, and fairness in FL scenarios. We prove that PUFFLE can be effective across diverse datasets, models, and data distributions, reducing the model unfairness up to 75%, with a maximum reduction in the utility of 17% in the worst-case scenario, while maintaining strict privacy guarantees during the FL training.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Income Prediction on Adult (IID)](<https://www.sota2.com/research/sota/income-prediction-on-adult-iid.md>): Income Prediction; Adult (IID); Accuracy: 82.94.

- [Object Detection on FACET (IID client shards)](<https://www.sota2.com/research/sota/object-detection-on-facet-iid-client-shards.md>): Object Detection; FACET (IID client shards); Overall mAP: 41.92.

- [Sentiment Prediction on TweetEval (IID)](<https://www.sota2.com/research/sota/sentiment-prediction-on-tweeteval-iid.md>): Sentiment Prediction; TweetEval (IID); Accuracy: 49.59.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2407.15224>)

[PDF](<https://arxiv.org/pdf/2407.15224.pdf>)