Summary
When automated systems act on behalf of users across different organizations, it is hard for those relying on these actions to know whether to trust them based only on the original producers information. The authors present a new way to package and manage evidence about trust that spans organizational boundaries, making it clear who issued what information and how to verify it independently. This system helps keep trust evidence consistent, reviewable, and usable even when problems or disputes arise. Their approach combines existing identity, authorization, and provenance tools into a reusable model for cross-domain trust.
What this means in practice
- •For security engineers: Design trust frameworks that allow secure delegation and verification across organizational boundaries for automated agents.
- •For cloud service operators: Implement interoperable trust-evidence envelopes to manage and verify cross-domain delegated actions and related provenance.
Abstract
Agentic systems increasingly invoke tools, services, data, and other agents across organizational boundaries, yet a relying party cannot assess a delegated action solely from producing-domain controls and records. This paper develops Trustworthiness as a Service (TaaS) through a synthesis of trustworthy-AI governance, agent security, distributed trust management, identity, provenance, assurance, and control-plane research. The analytical unit is a cross-domain reliance proposition that names the issuer, subject and action, relying party, administrative boundary, evidence dependencies, adverse condition, and required verification or adjudication semantics. The three-condition structural-externalization diagnostic identifies propositions that depend on multiple domains, require producer-independent reliance, and must remain reviewable after revocation, failure, conflicting records, or dispute. For such propositions, the paper specifies a trust-evidence envelope: an immutable workflow manifest linked to append-only, issuer-attributed attestations for task-scoped authority, policy and execution decisions, provenance, validity, disclosure, status, challenge, and recovery. A topology-neutral logical reference model assigns these functions to explicit roles and trust domains. Three analytical scenarios and the TaaS-Eval protocol proposal define manifests, independent consumers, hard gates, adversarial evidence tests, metrics, and reproducible artifact reporting. By composing established identity, authorization, provenance, assurance, and governance mechanisms around a bounded delegated action, TaaS provides a reusable profile for cross-domain reliance. It makes evidence dependencies, independent verification, challenge, and recovery explicit, supporting interoperable governance and future evaluation without treating producer assertions as ground truth.