Similarity-based Label Inference Attack against Training and Inference of Split Learning

arXiv:2203.05222v2 Announce Type: replace
Abstract: Split learning is a promising paradigm for privacy-preserving distributed learning. The learning model can be cut into multiple portions to be collaboratively trained at the participants by exchanging only the intermediate results at the cut layer. Understanding the security performance of split learning is critical for many privacy-sensitive applications. This paper shows that the exchanged intermediate results, including the smashed data (i.e., extracted features from the raw data) and gradients during training and inference of …

abstract arxiv cs.ai cs.cr cs.lg distributed distributed learning inference intermediate layer multiple paradigm performance privacy results security training type understanding