Binding Biometrics with AI Agent Identifiers for Delegation of Authority

2026-08-04

AI Summary

This work addresses the lack of traceable human authorization and accountability mechanisms for AI agents performing critical tasks by proposing the BIND framework, which introduces biometric cryptosystems into AI agent authorization for the first time. The framework leverages deep neural networks to extract facial features and integrates feature adaptation, fuzzy commitment, and Turbo error-correcting codes to generate a 1024-bit binary biometric key that securely binds user identity, agent permissions, and task constraints into a verifiable authorization token. Experimental results demonstrate that the system achieves a 96% genuine match rate at zero false acceptance rate, providing undeniable proof of human oversight over AI agents while enabling third-party auditors to verify identities and recover information in real time.

Abstract

The proliferation of agentic artificial intelligence (AI) systems has raised serious questions about the accountability for tasks performed by AI agents. Ideally, an AI agent must not be allowed to perform critical tasks without explicit authorization by a human operator. Since biometric recognition is one of the most reliable approaches for authenticating individuals, it has the potential to enable authenticated delegation of authority to AI agents. In this work, we present a framework called BIND, which leverages ideas from the field of biometric cryptosystems, to securely bind biometric data of the human user to the AI agent identity (ID) and authority scope (task-specific constraints) at the time of agent authorization. This token/identifier can be presented by the AI agent to an Identity Auditor, who simultaneously performs biometric authentication and recovers the agent ID and scope, thereby enabling real-time user authentication and establishing a non-repudiable proof of human control and delegation of authority. We also provide a practical implementation of the proposed BIND framework based on face features extracted using standard deep neural network models. To facilitate this implementation, we propose a feature adaptation module that transforms real-valued feature embeddings into fixed-length binary representations suitable for a fuzzy commitment construct based on turbo error correcting codes. Experiments demonstrate the practical feasibility of the proposed face cryptosystem, achieving a True Match Rate of $96\%$ at zero False Match Rate and supporting $1024$-bit agent tokens.

Problem

• AI agent
• delegation of authority
• biometric authentication
• accountability
• human control

Innovation

• biometric cryptosystem
• AI agent authorization
• fuzzy commitment
• feature adaptation
• non-repudiable delegation