Differentially Private Kernel Inducing Points using features from ScatterNets (DP-KIP-ScatterNet) for Privacy Preserving Data Distillation

arXiv:2301.13389v2 Announce Type: replace
Abstract: Data distillation aims to generate a small data set that closely mimics the performance of a given learning algorithm on the original data set. The distilled dataset is hence useful to simplify the training process thanks to its small data size. However, distilled data samples are not necessarily privacy-preserving, even if they are generally humanly indiscernible. To address this limitation, we introduce differentially private kernel inducing points (DP-KIP) for privacy-preserving data distillation. Unlike our original …

abstract algorithm arxiv cs.lg data data set dataset distillation features generate kernel performance privacy privacy preserving process set small small data stat.ml training type