AI Agents with Decentralized Identifiers and Verifiable Credentials

TL;DR

This paper introduces a framework for AI agents to establish trust using decentralized identifiers and verifiable credentials, enabling secure cross-domain interactions and trust relationships.

Contribution

It proposes a novel integration of W3C DIDs and VCs into AI agents, creating a self-sovereign identity system for trust establishment in multi-agent dialogues.

Findings

Technical feasibility demonstrated through prototype implementation.

Agents can authenticate and establish trust using DIDs and VCs.

Limitations identified when LLMs control security procedures.

Abstract

A fundamental limitation of current LLM-based AI agents is their inability to build differentiated trust among each other at the onset of an agent-to-agent dialogue. However, autonomous and interoperable trust establishment becomes essential once agents start to operate beyond isolated environments and engage in dialogues across individual or organizational boundaries. A promising way to fill this gap in Agentic AI is to equip agents with long-lived digital identities and introduce tamper-proof and flexible identity-bound attestations of agents, provisioned by commonly trusted third parties and designed for cross-domain verifiability. This article presents a conceptual framework and a prototypical multi-agent system, where each agent is endowed with a self-sovereign digital identity. It combines a unique and ledger-anchored W3C Decentralized Identifier (DID) of an agent with a set of third-party issued W3C Verifiable Credentials (VCs). This enables agents at the start of a dialog to prove ownership of their self-controlled DIDs for authentication purposes and to establish various cross-domain trust relationships through the spontaneous exchange of their self-hosted DID-bound VCs. A comprehensive evaluation of the prototypical implementation demonstrates technical feasibility but also reveals limitations once an agent's LLM is in sole charge to control the respective security procedures.