返回全部动态
Google 发布基于 TEE 的可验证隐私联邦学习系统
原标题：Toward provably private learning from federated data
AI 摘要
Google Research 宣布推出新一代联邦学习系统，利用可信执行环境（TEE）为数据匿名化提供可外部验证和审计的隐私保证，并将计算转移到服务器端以提升训练速度、准确率和设备覆盖。Gboard 已采用该系统部署英语和日语下一词预测模型，训练时间从过去的 1-2 个月大幅缩短。系统通过 Rekor 公开透明日志发布访问策略，相关 KMS 和数据处理二进制可从开源代码复现构建。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
October 2, 2026 Katharine Daly, Software Engineer, and Daniel Ramage, Research Director, Google Research We announce a new Federated Learning system that provides externally verifiable privacy guarantees while shifting computation to the server to improve training speed, accuracy, and device coverage. In 2017, Google introduced Federated Learning (FL) a machine learning technique that trains models across decentralized, private data. It has been used to power everyday helpful features, including
发布时间：2026-10-02 22:57
抓取时间：2026-10-02 23:00
来源机构：Google Research