Delphi: A Cryptographic Inference Service for Neural Networks | USENIXusenix_logo_notag_white

Authors:  Pratyush Mishra, Ryan Lehmkuhl, Akshayaram Srinivasan, Wenting Zheng, and Raluca Ada Popa, UC Berkeley Abstract:  Many companies provide neural network prediction services to users for a wide range of applications. However, current prediction systems compromise one party's privacy: either the user has to send sensitive inputs to the service provider for classification, or the service provider must store its proprietary neural networks on the user's device. The former harms the persona

1 mentions: @bigdata
Date: 2020/01/15 23:21

Referring Tweets

@bigdata Delphi from @ucbrise is a secure prediction system that allows two parties to run a neural network inference without revealing either party's data #DeepLearning #inference t.co/X1Z1jfu72t t.co/7JLUBbGRaI

Related Entries

Read more [2001.00888] Towards Scalable Dataframe Systemscontact arXivarXiv Twitter
0 users, 1 mentions 2020/01/16 20:20
Read more Checkmate · Train huge neural nets without running out of GPU memory
0 users, 1 mentions 2020/01/17 02:20
Read more Scaling Machine Learning Productivity at LinkedIn | LinkedIn Engineering
0 users, 1 mentions 2020/01/21 21:52
Read more The Data Exchange
0 users, 2 mentions 2020/02/21 05:20
Read more Viewing machine learning and data science applications as sociotechnical systems – The Data Exchange
0 users, 3 mentions 2020/06/11 13:30