RAF-GI: Towards Robust, Accurate and Fast-Convergent Gradient Inversion Attack in Federated Learning

arXiv:2403.08383v1 Announce Type: new
Abstract: Federated learning (FL) empowers privacy-preservation in model training by only exposing users' model gradients. Yet, FL users are susceptible to the gradient inversion (GI) attack which can reconstruct ground-truth training data such as images based on model gradients. However, reconstructing high-resolution images by existing GI attack works faces two challenges: inferior accuracy and slow-convergence, especially when the context is complicated, e.g., the training batch size is much greater than 1 on each FL user. To …

abstract arxiv cs.cv data federated learning gradient ground-truth however images preservation privacy robust training training data truth type