3 papers
cs.LG2020
Effectiveness of MPC-friendly Softmax Replacement
Marcel Keller, Ke Sun
Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party c…
cs.CR2019
A Note on Our Submission to Track 4 of iDASH 2019
Marcel Keller, Ke Sun
iDASH is a competition soliciting implementations of cryptographic schemes of interest in the context of biology. In 2019, one track asked for multi-party computation implementatio…
cs.CR2019
Secure Evaluation of Quantized Neural Networks
Anders Dalskov, Daniel Escudero, Marcel Keller
We investigate two questions in this paper: First, we ask to what extent "MPC friendly" models are already supported by major Machine Learning frameworks such as TensorFlow or PyTo…