EXACT: Extensive Attack for Split Learning. (arXiv:2305.12997v2 [cs.LG] UPDATED)

Privacy-Preserving machine learning (PPML) can help us train and deploy
models that utilize private information. In particular, on-device Machine
Learning allows us to completely avoid sharing information with a third-party
server during inference. However, on-device models are typically less accurate
when compared to the server counterparts due to the fact that (1) they
typically only rely on a small set of on-device features and (2) they need to
be small enough to run efficiently on end-user devices. Split Learning (SL) …

attack device fact information machine machine learning party privacy private server sharing split learning third third-party train