Data-driven decision-making and AI applications present exciting new opportunities delivering widespread benefits. The rapid adoption of such applications triggers legitimate concerns about loss of privacy and misuse of personal data. This leads to a growing and pervasive tension between harvesting ubiquitous data on the Web and the need to protect individuals. Decentralised personal data stores (PDS) such as Solid are frameworks designed to give individuals ultimate control over their personal data. But current PDS approaches have limited support for ensuring privacy when computations combine data spread across users. Secure Multi-Party Computation (MPC) is a well-known subfield of cryptography, enabling multiple autonomous parties to collaboratively compute a function while ensuring the secrecy of inputs (input privacy). These two technologies complement each other, but existing practices fall short in addressing the requirements and challenges of introducing MPC in a PDS environment. For the first time, we propose a modular design for integrating MPC with Solid while respecting the requirements of decentralisation in this context. Our architecture, Libertas, requires no protocol level changes in the underlying design of Solid, and can be adapted to other PDS. We further show how this can be combined with existing differential privacy techniques to also ensure output privacy. We use empirical benchmarks to inform and evaluate our implementation and design choices. We show the technical feasibility and scalability pattern of the proposed system in two novel scenarios -- 1) empowering gig workers with aggregate computations on their earnings data; and 2) generating high-quality differentially-private synthetic data without requiring a trusted centre. With this, we demonstrate the linear scalability of Libertas, and gained insights about compute optimisations under such an architecture.

翻译：摘要：数据驱动的决策与人工智能应用带来了令人振奋的新机遇，为社会带来广泛福祉。此类应用的快速普及引发了人们对隐私丧失及个人数据滥用的合理关切，这导致在采集网络上无处不在的数据与保护个体需求之间日益加剧的普遍矛盾。诸如Solid等去中心化个人数据存储（PDS）框架旨在赋予个体对其个人数据的最终控制权。然而，当计算涉及跨用户数据聚合时，当前的PDS方法在保障隐私方面支持有限。安全多方计算（MPC）是密码学中一个著名子领域，能够使多个自主参与方在确保输入保密性（输入隐私）的前提下协同计算某一函数。这两项技术相辅相成，但现有实践在应对将MPC引入PDS环境的需求与挑战方面仍存在不足。我们首次提出了一种模块化设计方案，在尊重该背景下去中心化要求的同时，将MPC与Solid集成。我们的架构Libertas无需对Solid底层设计进行协议级更改，并可适配至其他PDS。我们进一步展示了如何将其与现有差分隐私技术结合，从而同时确保输出隐私。我们通过实证基准测试来验证并评估我们的实现与设计选择。我们在两个新颖场景中展示了所提系统的技术可行性及可扩展性模式：1）赋予零工工作者对其收入数据进行聚合计算的能力；2）在无需可信中心的情况下生成高质量的差分隐私合成数据。借此，我们证明了Libertas的线性可扩展性，并获得了此类架构下计算优化的洞见。