Federating trust: network orchestration for cross-boundary zero trust

Abstract

Zero Trust is an emerging security paradigm that does away with implicit zones of trust commonly employed within static, defense-in-depth, enterprise architectures. One of the core tenets of Zero Trust is that resource access is determined by dynamic policy - an intersection of trust in a user, the supporting application or service, the underlying network, and the devices which hold or process data. Establishing this overall assessment of trust serves well for centralized architectures where an administrator can establish and assess each of these trust enablers, such as in an enterprise network. However, shifting workloads to remote access, bring your own device (BYOD), and cloud hosting of collaborative services, to name a few, all challenge the ability of an administrator to effectively establish a complete Zero Trust architecture due to the inability to fully trust each component. This shift away from centrally managed architectures reveal a significant challenge in achieving complete Zero Trust: security is a function of many interactions, many of which an administer has no control over. Recently the term "Zero Trust 2.0" was coined as an evolution to Zero Trust which establishes identity as the new perimeter via an orchestration layer and machine learning capabilities~\cite{trust}. However, this functionality still remains tied to centrally controlled architectures where an administrator can link together products and solutions to achieve a desired level of security. We argue that this orchestration needs to expand beyond these common enterprise boundaries in a way that trust can be guaranteed across disparate systems, networks, and servicers. Similar to identity federation, where a user can use credentials from one provider to access another competitors platform, federation of trust should serve as a guarantee for security across networks. In the remaining sections we propose what this trust federation mechanism could potentially look like.