Practical Secure Aggregation for Privacy-Preserving Machine Learning论文阅读笔记

提出了一种安全聚合算法,Secure Aggregation算法,可以使得在多方学习(如联邦学习)中各方client在不暴露各自梯度的情况下实现梯度的聚合。

实验

我们提出了安全计算向量之和的算法,它满足常数迭代轮次、低通信代价、对故障具有鲁棒性、且有一个可信度受限的server。server有两种角色:一是想其他参与方发送信息,二是计算最终结果。
鉴于联邦学习系统的缺点(对于隐私的要求以及终端不同步的问题),急切需要一种安全聚合算法来解决这些问题:

  1. 操作高维数据;
  2. 提高通信效率;
  3. 对终端用户的失联的鲁棒性;
  4. 在以server为中心且不被授权的网络模型中实现尽可能强的安全性。
密码学

分别讲了秘密共享、密钥协商、认证加密、伪随机数生成、数字签名、公钥基础设施的知识。
几个算法介绍:
S S . s h a r e ( s , t , U ) : \bold{SS.share}(s,t,\mathcal{U}): SS.share(s,t,U):共享算法,输入为秘密 s s s,代表用户ID的 n n n个域元素的集合 U \mathcal{U} U,和一个阈值 t ≤ ∣ U ∣ t\le |\mathcal{U}| tU,输出为共享 s u s_u su的集合,其中 u ∈ U u\in \mathcal{U} uU
S S . r e c o n ( { ( u , s u ) } u ∈ V , t ) : \bold{SS.recon}(\{(u,s_u)\}_{u\in \mathcal{V}}, t): SS.recon({ (u,su)}uV,t):,重构函数,输入为阈值 t t t,参与共享的用户子集 V ⊆ U \mathcal{V}\subseteq \mathcal{U} VU且满足 ∣ V ∣ ≥ t |\mathcal{V}|\ge t Vt,输出为域元素 s s s

K A . p a r a m ( k ) : \bold{KA.param}(k): KA.param(

Privacy-preserving machine learning is becoming increasingly important in today's world where data privacy is a major concern. Federated learning and secure aggregation are two techniques that can be used to achieve privacy-preserving machine learning. Federated learning is a technique where the machine learning model is trained on data that is distributed across multiple devices or servers. In this technique, the model is sent to the devices or servers, and the devices or servers perform the training locally on their own data. The trained model updates are then sent back to a central server, where they are aggregated to create a new version of the model. The key advantage of federated learning is that the data remains on the devices or servers, which helps to protect the privacy of the data. Secure aggregation is a technique that can be used to protect the privacy of the model updates that are sent to the central server. In this technique, the updates are encrypted before they are sent to the central server. The central server then performs the aggregation operation on the encrypted updates, and the result is sent back to the devices or servers. The devices or servers can then decrypt the result to obtain the updated model. By combining federated learning and secure aggregation, it is possible to achieve privacy-preserving machine learning. This approach allows for the training of machine learning models on sensitive data while protecting the privacy of the data and the model updates.
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值