TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Machine Learning Privacy with Fully Homomorphic Encryption

6 点作者 zacchj超过 2 年前

1 comment

eternalban超过 2 年前
The paper for the FFHE: <a href="https:&#x2F;&#x2F;eprint.iacr.org&#x2F;2016&#x2F;870.pdf" rel="nofollow">https:&#x2F;&#x2F;eprint.iacr.org&#x2F;2016&#x2F;870.pdf</a><p>tldr here is that Zama believes privacy for the model owner (not the user) can be satisfied by having a trusted 3rd party host the (unencrypted) model and simply apply FHE to user data (which is faster). And that&#x27;s the their solution.