HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems
Asiri Dalugoda

TL;DR
HDP is a lightweight cryptographic protocol designed to securely verify human authorization in multi-agent AI systems, ensuring accountability through an append-only, verifiable provenance chain.
Contribution
The paper introduces HDP, a novel token-based scheme that cryptographically captures and verifies human delegation provenance in agentic AI systems, addressing gaps in existing standards.
Findings
HDP enables offline verification of human delegation with only a public key and session ID.
HDP's design is distinct from OAuth 2.0, JWT, UCAN, and IPP in multi-hop, append-only provenance.
HDP is published as an IETF draft and has a publicly available TypeScript SDK.
Abstract
Agentic AI systems increasingly execute consequential actions on behalf of human principals, delegating tasks through multi-step chains of autonomous agents. No existing standard addresses a fundamental accountability gap: verifying that terminal actions in a delegation chain were genuinely authorized by a human principal, through what chain of delegation, and under what scope. This paper presents the Human Delegation Provenance (HDP) protocol, a lightweight token-based scheme that cryptographically captures and verifies human authorization context in multi-agent systems. An HDP token binds a human authorization event to a session, records each agent's delegation action as a signed hop in an append-only chain, and enables any participant to verify the full provenance record using only the issuer's Ed25519 public key and the current session identifier. Verification is fully offline,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
