Software Open Access
JOSEPH P. NEAR; DAVID DARAIS; CHIKE ABUAH; TIM STEVENS; PRANAV GADDAMADUGU; LUN WANG; NEEL SOMANI; MU ZHANG; NIKHIL SHARMA; ALEX SHAN; DAWN SONG
Duet is an expressive higher-order language, linear type system and tool for automatically verifying differential privacy of arbitrary higher-order programs. In addition to general purpose programming, it supports encoding machine learning algorithms such as stochastic gradient descent, as well as common auxiliary data analysis tasks such as clipping, normalization and hyperparameter tuning.
Current version is available at the GitHub repository: https://github.com/uvm-plaid/duet