Deep Leakage from Model in Federated Learning. (arXiv:2206.04887v1 [cs.LG])

Distributed machine learning has been widely used in recent years to tackle
the large and complex dataset problem. Therewith, the security of distributed
learning has also drawn increasing attentions from both academia and industry.
In this context, federated learning (FL) was developed as a "secure"
distributed learning by maintaining private training data locally and only
public model gradients are communicated between. However, to date, a variety of
gradient leakage attacks have been proposed for this procedure and prove that
it …

lg