PrivacyRaven: Comprehensive Privacy Testing for Deep Learning

title	PrivacyRaven: Comprehensive Privacy Testing for Deep Learning
date	2020-09-26
authors	Suha Hussain
conference	OpenMined Privacy Conference 2020 Empire Hacking
resources	label path Slides PrivacyRaven_OpenMined.pdf label url Recording https://www.youtube.com/watch?v=F46lX5VIoas&t=2h21m50s label url PrivacyRaven https://github.com/trailofbits/privacyraven

PrivacyRaven is a comprehensive privacy testing suite for deep learning systems optimized for usability and efficiency. With PrivacyRaven, users can determine the susceptibility of a model to privacy attacks, systematically evaluate different privacy preserving machine learning techniques, develop novel privacy metrics and attacks, and repurpose attacks for data provenance and other use cases. Model extraction, membership inference, model inversion, and other privacy attacks can be quickly prototyped and launched using its modular design.