Secure Shapley Value for Cross-Silo Federated Learning
Secure Shapley Value for Cross-Silo Federated Learning
复制标题
DOI：
10.14778/3587136.3587141
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Shuyuan Zheng;Yang Cao;Masatoshi Yoshikawa
中科院分区：
文献类型：
--
作者：
Shuyuan Zheng;Yang Cao;Masatoshi Yoshikawa
Shapley值（SV）是跨筒仓联合学习（cross-silo federated learning，cross-silo FL）中贡献评估的公平和原则性指标，其中组织，即，客户端在参数服务器的协调下协作地训练预测模型。然而，现有的用于FL的SV计算方法假设服务器可以访问原始FL模型和公共测试数据。考虑到对FL模型的新兴隐私攻击以及测试数据可能是客户的私人资产的事实，这在实践中可能不是一个有效的假设。因此，我们调查的问题，安全SV计算跨筒仓FL。我们首先提出HESV，一个服务器的解决方案，完全基于同态加密（HE）的隐私保护，这在效率上有局限性。为了克服这些限制，我们提出SecSV，一个有效的两个服务器协议，具有以下新功能。首先，SecSV利用混合隐私保护方案来避免测试数据和模型之间的密文-密文乘法，这在HE下是非常昂贵的。其次，提出了一种安全的矩阵乘法算法。第三，SecSV策略性地识别和跳过一些测试样本，而不会显著影响评估准确性。我们的实验表明，SecSV的速度是HESV的7.2- 36.6倍，而计算SV的精度损失有限。
The Shapley value (SV) is a fair and principled metric for contribution evaluation in cross-silo federated learning (cross-silo FL), wherein organizations, i.e., clients, collaboratively train prediction models with the coordination of a parameter server. However, existing SV calculation methods for FL assume that the server can access the raw FL models and public test data. This may not be a valid assumption in practice considering the emerging privacy attacks on FL models and the fact that test data might be clients' private assets. Hence, we investigate the problem of secure SV calculation for cross-silo FL. We first propose HESV , a one-server solution based solely on homomorphic encryption (HE) for privacy protection, which has limitations in efficiency. To overcome these limitations, we propose SecSV , an efficient two-server protocol with the following novel features. First, SecSV utilizes a hybrid privacy protection scheme to avoid ciphertext-ciphertext multiplications between test data and models, which are extremely expensive under HE. Second, an efficient secure matrix multiplication method is proposed for SecSV. Third, SecSV strategically identifies and skips some test samples without significantly affecting the evaluation accuracy. Our experiments demonstrate that SecSV is 7.2--36.6× as fast as HESV, with a limited loss in the accuracy of calculated SVs.