FLGAN: GAN-Based Unbiased Federated Learning Under Non-IID Settings **Abstract:** Federated Learning (FL) suffers from low convergence and significant accuracy loss due to local biases caused by non-Independent and Identically Distributed (non-IID) data. To enhance the non-IID FL performance, a straightforward idea is to leverage the Generative Adversarial Network (GAN) to mitigate local biases using synthesized samples. However, existing GAN-based solutions have inherent limitations, which do not support non-IID data and even compromise user privacy. To address these issues, we propose a GAN-based unbiased FL scheme, called FLGAN, to mitigate local biases using synthesized samples generated by GAN while preserving user-level privacy in the FL setting. Specifically, FLGAN first presents a federated GAN algorithm using the divide-and-conquer strategy that eliminates the problem of model collapse in non-IID settings. To guarantee user-level privacy, FLGAN then exploits Fully Homomorphic Encryption (FHE) to design the privacy-preserving GAN augmentation method for the unbiased FL. Extensive experiments show that FLGAN achieves unbiased FL with 10% — 60% accuracy improvement compared with two state-of-the-art FL baselines (i.e., FedAvg and FedSGD) trained under different non-IID settings. The FHE-based privacy guarantees only cost about 0.53% of the total overhead in FLGAN. **Keywords:** Federated learning, fully homomorphic encryption, GAN, non-IID, user-level privacy.FLGAN: GAN-Based Unbiased Federated Learning Under Non-IID Settings **Abstract:** Federated Learning (FL) suffers from low convergence and significant accuracy loss due to local biases caused by non-Independent and Identically Distributed (non-IID) data. To enhance the non-IID FL performance, a straightforward idea is to leverage the Generative Adversarial Network (GAN) to mitigate local biases using synthesized samples. However, existing GAN-based solutions have inherent limitations, which do not support non-IID data and even compromise user privacy. To address these issues, we propose a GAN-based unbiased FL scheme, called FLGAN, to mitigate local biases using synthesized samples generated by GAN while preserving user-level privacy in the FL setting. Specifically, FLGAN first presents a federated GAN algorithm using the divide-and-conquer strategy that eliminates the problem of model collapse in non-IID settings. To guarantee user-level privacy, FLGAN then exploits Fully Homomorphic Encryption (FHE) to design the privacy-preserving GAN augmentation method for the unbiased FL. Extensive experiments show that FLGAN achieves unbiased FL with 10% — 60% accuracy improvement compared with two state-of-the-art FL baselines (i.e., FedAvg and FedSGD) trained under different non-IID settings. The FHE-based privacy guarantees only cost about 0.53% of the total overhead in FLGAN. **Keywords:** Federated learning, fully homomorphic encryption, GAN, non-IID, user-level privacy.