Miao Pan

Differentially Private Functional Mechanism for Generative Adversarial Networks

2019

In recent years, generative adversarial network (GAN) has attracted great attention due to its impressive performance and potential numerous applications, such as data augmentation, real-like image synthesis, image compression improvement, etc. The generator in GAN …

Fed2VAEs: An Efficient Privacy-Preserving Federated Learning Approach Based on Variational Autoencoders

2024

Recently, federated learning (FL) has been threat-ened by the gradient inversion attack that infers user-private data from shared gradients. To cope with this problem, the differential privacy (DP) technique is widely employed in FL. However, …

Spectral attention for transformers: frequency-domain filtering of attention maps

2026 · Journal of King Saud University - Computer and Information Sciences

Abstract This paper introduces spectral attention, which filters the attention score matrix directly in the frequency domain via FFT/IFFT with learnable, per-head masks. This complements the time-domain view by enabling explicit control over low-, mid-, …