News for hackers. Stuff that matters.
Re:Intel to Build Silicon for Fully Homomorphic Encryption by xsamgreen on Tuesday March 09, 2021 @12:44PM (#26401319)
10^5 speed up will get them to 10x slower than plaintext processing of deep neural networks. See page 15 of DARPA's BAA:

https://beta.sam.gov/api/prod/opps/v3/opportunities/resource...

For simple computing like logistic regression, they aim to be as fast as plaintext.

There are no comments on this comment yet.