A three-party framework that customizes binarized neural networks with distillation and separable convolutions to speed up privacy-preserving inference.
ACM Transactions on Computation Theory (TOCT) 6(3), 1–36 (2014)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
CBNN: 3-Party Secure Framework for Customized Binary Neural Networks Inference
A three-party framework that customizes binarized neural networks with distillation and separable convolutions to speed up privacy-preserving inference.