论文标题
分布式数据和应用程序的差异保密
Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation
论文作者
论文摘要
计算实价矢量的嘈杂总和是差异私人学习和统计数据中的重要原始性。在私人联合学习应用程序中，这些向量由客户设备持有，导致分布式求和问题。对于此问题的标准安全多方计算（SMC）方案容易受到中毒攻击的影响，在这种情况下，客户可能会对总和产生很大的影响，而无需检测到。 在这项工作中，我们在最近在PRIO研究的多服务器环境中提出了一种抗毒私人求和协议。我们提出了矢量总和的协议，该协议验证了每个贡献的欧几里得规范近似限制。我们表明，通过将SMC中的安全性限制放大到诸如保证之类的差异隐私之类的情况下，就可以在通信需求以及客户端计算方面改善PRIO。与SMC算法不可避免地将整数呈现到大量有限字段的元素不同，我们的算法对整数/REAL来起作用，这可能允许额外的效率。
Computing the noisy sum of real-valued vectors is an important primitive in differentially private learning and statistics. In private federated learning applications, these vectors are held by client devices, leading to a distributed summation problem. Standard Secure Multiparty Computation (SMC) protocols for this problem are susceptible to poisoning attacks, where a client may have a large influence on the sum, without being detected. In this work, we propose a poisoning-robust private summation protocol in the multiple-server setting, recently studied in PRIO. We present a protocol for vector summation that verifies that the Euclidean norm of each contribution is approximately bounded. We show that by relaxing the security constraint in SMC to a differential privacy like guarantee, one can improve over PRIO in terms of communication requirements as well as the client-side computation. Unlike SMC algorithms that inevitably cast integers to elements of a large finite field, our algorithms work over integers/reals, which may allow for additional efficiencies.
