An Adaptive Communication-Efficient Federated Learning to Resist Gradient-Based Reconstruction Attacks

Table 3

The evaluation metrics of the GAN-based attacks with the MNIST dataset in different frequencies.

Method	Iterations	Communication frequency	SSIM	MSE
GAN	100	1	0.6289	41.9540
GAN	100	2	0.6347	40.3287
GAN	100	3	0.6110	43.9704
GAN	100	4	0.6009	42.4333
GAN	100	5	0.5914	46.7876