TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Orion: A Homomorphic Encryption Framework for Deep Learning [pdf]

2 pointsby bikenagaabout 2 months ago

1 comment

theamkabout 2 months ago
btw, link is marked wrong - it&#x27;s not pdf, it takes you to arxiv page, with links to pdf or HTML view. The [pdf] marker is only for links to pdf files directly, to avoid surprises.<p>The interesting part here is table 2, especially Flops(M) and Time(s) columns. Seems that homomorphic calculations achieve about 0.1 to 1.5 MFlops&#x2F;sec on Xeon Platinum @ 2.3 GHz w&#x2F; 512 GB RAM. The same CPU benchmarks about 15,000 MFlops&#x2F;sec for regular calculations, and would probably less than 1GB of RAM for those tiny modes.<p>Yeah, maybe they &quot;outperform state-of-the-art by 2.38×&quot;, but they are still wildly impractical.
评论 #43605560 未加载