As privacy concerns and regulatory constraints on data protection continue to grow, the distribution of collected data has become more dispersed, resembling a ”data silo” style. To harness these data effectively without exchanging raw data, federated learning has emerged as a prominent solution. However, distributions of user-generated data often exhibit imbalances between devices and labels, which adversely affect model performance, especially in the presence of adversarial attacks, making models more susceptible. To address the challenge of balancing natural accuracy and robustness in federated training, especially under skewed label distribution scenarios, we propose a novel approach based on Generative Adversarial Networks for Federated Adversarial Training (GANFAT). GANFAT leverages GAN to enhance the authenticity and effectiveness of adversarial samples and addresses label distribution skew issues by incorporating class probability distribution information. Through a balanced interplay of natural accuracy loss and adversarial loss, GANFAT demonstrates significantly superior performance across multiple datasets under various settings compared to other frameworks. Particularly on the SVHN dataset, GANFAT achieves a remarkable 9.30% enhancement in robustness against FGSM attacks compared to the best baseline method (FedRBN). On the CIFAR-100 dataset, GANFAT showcases a noteworthy 6.68% improvement in natural accuracy compared to the best baseline method (CalFAT). GANFAT provides a powerful solution for confronting diverse attacks, yielding models comparable to those produced by centralized training. Experimental results underscore GANFAT’s outstanding performance, offering a robust solution for scenarios characterized by uneven data distribution and adversarial attacks.

中文翻译：

---

GANFAT：具有标签分布偏差的鲁棒联合对抗学习


随着隐私问题和数据保护监管限制的不断增加，收集到的数据的分布变得更加分散，类似于“数据孤岛”风格。为了在不交换原始数据的情况下有效利用这些数据，联邦学习已成为一种突出的解决方案。然而，用户生成的数据的分布通常会表现出设备和标签之间的不平衡，这会对模型性能产生不利影响，特别是在存在对抗性攻击的情况下，使模型更容易受到影响。为了解决联邦训练中平衡自然准确性和鲁棒性的挑战，特别是在倾斜的标签分布场景下，我们提出了一种基于联邦对抗训练生成对抗网络（GANFAT）的新方法。 GANFAT 利用 GAN 来增强对抗样本的真实性和有效性，并通过合并类别概率分布信息来解决标签分布偏差问题。通过自然准确性损失和对抗性损失的平衡相互作用，与其他框架相比，GANFAT 在各种设置下的多个数据集上表现出了显着优越的性能。特别是在 SVHN 数据集上，与最佳基线方法（FedRBN）相比，GANFAT 针对 FGSM 攻击的鲁棒性显着提高了 9.30%。在 CIFAR-100 数据集上，与最佳基线方法 (CalFAT) 相比，GANFAT 的自然准确性显着提高了 6.68%。 GANFAT 提供了应对各种攻击的强大解决方案，产生的模型可与集中训练产生的模型相媲美。 实验结果凸显了 GANFAT 的出色性能，为数据分布不均匀和对抗性攻击的场景提供了强大的解决方案。