[其他] ICML-Gradient Disaggregation Breaking Privacy in Federated Learning by Reco ... [推广有奖]

1关注
167
粉丝

已卖：5690份资源

泰斗

还不是VIP/贵宾

威望: 0 级
论坛币: 13312 个
通用积分: 769.6789
学术水平: 459 点
热心指数: 484 点
信用等级: 414 点
经验: 116409 点
帖子: 4688
精华: 0
在线时间: 16731 小时
注册时间: 2013-1-2
最后登录: 2026-2-9

楼主

Mujahida

发表于 2025-7-28 09:15:18 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Gradient Disaggregation: Breaking Privacy in Federated Learning by
         Reconstructing the User Participant Matrix

   Maximilian Lam 1 Gu-Yeon Wei 1 David Brooks 1 Vijay Janapa Reddi 1 Michael Mitzenmacher 1

         Abstract             or wearables, and maintaining the integrity of their data is a
We show that aggregated model updates in fed-    critical issue. Already, federated learning has been deployed
erated learning may be insecure. An untrusted    by many maj ...