FedSmarteum: Secure Federated Matrix Factorization Using Smart Contracts for Multi-Cloud Supply Chain

Abstract

With increased awareness comes unprecedented expectations. We live in a digital, cloud era wherein the underlying information architectures are expected to be elastic, secure, resilient, and handle petabyte scaling. The expectation of epic proportions from the next generation of the data frameworks is to not only do all of the above but also build it on a foundation of trust and explainability across multi-organization business networks. From cloud providers to automobile industries or even vaccine manufacturers, a typical supply chain consists of complex networks of suppliers, manufacturers, distributors, retailers, auditors, and consumers. With cloud providers, even though there is an increased focus on self-service or cloud provider-managed SaaS (Software-as-a-service), a portion of sales for an enterprise customer occurs the old-fashioned way with the sales department drawing up a purchase order for the procurement process. In many cases, there could be several disjoint, not fully digitized strings of suppliers behind the scenes. This leaves the buyer unbeknownst and unaware of the state of their order in real-time as it is challenging to build machine learning and AI-based systems for order fulfillment, time and cost predictive models, share data transparently and issue remediations when multiple organizations are involved to fulfill an order. In this dissertation, motivated by challenges in the industry, we propose a decentralized distributed system that can be considered as a building block for supply chain infrastructures, regardless of industry. The design goal of our system is to streamline complex non-repudiated transaction workflows by efficient handling of enterprise-scale purchase orders. We present transparent alternatives in real-time to customers based on model inference to respond to prediction requests. To further support this, we build a recommendation system model (Matrix Factorization) that is trained using Federated Learning on an Ethereum blockchain network. We leverage smart contracts that allow decentralized serverless aggregation to update localized items vectors. Furthermore, we utilize Homomorphic Encryption (HE) to allow sharing the encrypted gradients over the network while maintaining their privacy. Based on our results, we argue that training a model over a serverless Blockchain network using smart contracts will provide the same accuracy as in a centralized model while maintaining our serverless model privacy and reducing the overhead communication to a central server. Finally, we assert such a system that provides transparency, audit-ready and deep insights into supply chain operations for enterprise cloud customers resulting in cost savings and higher Quality of Service (QoS).