Temporal Gradient Inversion Attacks with Robust Optimization. (arXiv:2306.07883v1 [cs.LG])

Federated Learning (FL) has emerged as a promising approach for collaborative
model training without sharing private data. However, privacy concerns
regarding information exchanged during FL have received significant research
attention. Gradient Inversion Attacks (GIAs) have been proposed to reconstruct
the private data retained by local clients from the exchanged gradients. While
recovering private data, the data dimensions and the model complexity increase,
which thwart data reconstruction by GIAs. Existing methods adopt prior
knowledge about private data to overcome those challenges. …

attacks attention clients data federated learning information local model training optimization privacy privacy concerns private private data research sharing temporal training