May 10, 2021 · A library for end-to-end secure 2-party DNN inference, that provides the first secure implementations of an RNN operating on time series sensor data.
We build on top of our novel protocols to build SIRNN, a library for end-to-end secure 2-party DNN inference, that provides the first secure implementations of ...
A library for end-to-end secure 2-party DNN inference, that provides the first secure implementations of an RNN operating on time series sensor data.
Duration: 15:26
Posted: May 27, 2021
Posted: May 27, 2021
May 27, 2024 · Has anyone read the paper " SIRNN: A Math Library for Secure RNN Inference "? I'm having a very hard time understanding the reciprocal and ...
Our evaluation shows that SIRNN achieves up to three orders of magnitude of performance improvement when compared to inference of these models using an existing ...
Explore SIRNN, a math library enabling secure RNN inference, covering applications, challenges, optimizations, and performance evaluations for ...
Duration: 1:00
Posted: May 1, 2021
Posted: May 1, 2021
Duration: 14:55
Posted: Jan 27, 2022
Posted: Jan 27, 2022
EzPC: Programmable, Efficient, and Scalable Secure Two-Party Computation for Machine Learning. Nishanth Chandran, Divya Gupta, Aseem Rastogi, Rahul Sharma, ...