← Search

Hewang Nie

2 accepted papers

2025

FedDiT: Federated Learning by Distillation Token Enhanced Vision Transformer

ICASSP 2025accepted

Federated learning (FL) is a promising approach for privacy-preserving machine learning, enabling collaborative model training across distributed devices without sharing raw data. However, FL faces significant challenges due to the nonindependent and identically distributed (non-IID) nature of data…

Cited by 0SourceScholar
2025

Optimized Dynamic Watermarking for Audio DNNs with Adaptive Embedding and Boundary Sampling

ICASSP 2025accepted

The intensified concerns arising from the widespread adoption of deep learning have led to increased scrutiny of intellectual property protection in DNN models. Existing audio watermarking techniques, predominantly based on traditional signal processing methods, struggle to balance robustness, imper…

Cited by 0SourceScholar