A Decentralized Authorization and Security Framework for Distributed Research Workflows

Abstract

Research challenges such as climate change and the search for habitable planets increasingly use academic and commercial computing resources distributed across different institutions and physical sites. Furthermore, such analyses often require a level of automation that precludes direct human interaction, and securing these workflows involves adherence to security policies across institutions. In this paper, we present a decentralized authorization and security framework that enables researchers to utilize resources across different sites while allowing service providers to maintain autonomy over their secrets and authorization policies. We describe this framework as part of the Tapis platform, a web-based, hosted API used by researchers from multiple institutions, and we measure the performance of various authorization and security queries, including cross-site queries. We conclude with two use case studies -- a project at the University of Hawaii to study climate change and the NASA NEID telescope project that searches the galaxy for exoplanets.