# Using adversarial images to improve outcomes of federated learning for non-IID data

Source: [Using adversarial images to improve outcomes of federated learning for non-IID data](<https://www.sota2.com/research/paper/68fa6cc01e209131cea35caa>)

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

Data updated: 2025-10-26T00:17:38.470Z

Authors: Anastasiya Danilenka, Maria Ganzha, Marcin Paprzycki, Jacek Ma\\'ndziuk

Published: 2022-06-16T12:37:58.000Z

## Abstract

One of the important problems in federated learning is how to deal with unbalanced data. This contribution introduces a novel technique designed to deal with label skewed non-IID data, using adversarial inputs, created by the I-FGSM method. Adversarial inputs guide the training process and allow the Weighted Federated Averaging to give more importance to clients with 'selected' local label distributions. Experimental results, gathered from image classification tasks, for MNIST and CIFAR-10 datasets, are reported and analyzed.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2206.08124>)

[PDF](<https://arxiv.org/pdf/2206.08124.pdf>)