Membership Inference Attacks and Defenses in Neural Network Pruning. (arXiv:2202.03335v2 [cs.CR] UPDATED)

Neural network pruning has been an essential technique to reduce the
computation and memory requirements for using deep neural networks for
resource-constrained devices. Most existing research focuses primarily on
balancing the sparsity and accuracy of a pruned neural network by strategically
removing insignificant parameters and retraining the pruned model. Such efforts
on reusing training samples pose serious privacy risks due to increased
memorization, which, however, has not been investigated yet.

In this paper, we conduct the first analysis of privacy …

attacks network neural network