Differentially Private CutMix for Split Learning with Vision Transformer

no code implementations • 28 Oct 2022 • Seungeun Oh, Jihong Park, Sihun Baek, Hyelin Nam, Praneeth Vepakomma, Ramesh Raskar, Mehdi Bennis, Seong-Lyun Kim

Split learning (SL) detours this by communicating smashed data at a cut-layer, yet suffers from data privacy leakage and large communication costs caused by high similarity between ViT' s smashed data and input data.

Federated Learning Privacy Preserving

Visual Transformer Meets CutMix for Improved Accuracy, Communication Efficiency, and Data Privacy in Split Learning

no code implementations • 1 Jul 2022 • Sihun Baek, Jihong Park, Praneeth Vepakomma, Ramesh Raskar, Mehdi Bennis, Seong-Lyun Kim

Leveraging this, we develop a novel SL framework for ViT, coined CutMixSL, communicating CutSmashed data.

Data Augmentation Federated Learning