AITH: A Post-Quantum Continuous Delegation Protocol for Human-AI Trust Establishment

TL;DR

AITH is a novel post-quantum protocol for continuous human-AI trust delegation, enabling secure, efficient, and auditable trust management for autonomous AI agents.

Contribution

It introduces a post-quantum, cryptographically efficient trust delegation protocol with real-time boundary enforcement and tamper-evident logging, validated through formal verification and adversarial testing.

Findings

Achieves 4.7 million operations per second with boundary checks

Enforces trust constraints with zero cryptographic overhead on critical path

Resolves 12 vulnerabilities in multi-model adversarial audits

Abstract

The rapid deployment of AI agents acting autonomously on behalf of human principals has outpaced the development of cryptographic protocols for establishing, bounding, and revoking human-AI trust relationships. Existing frameworks (TLS, OAuth 2.0, Macaroons) assume deterministic software and cannot address probabilistic AI agents operating continuously within variable trust boundaries. We present AITH (AI Trust Handshake), a post-quantum continuous delegation protocol. AITH introduces: (1) a Continuous Delegation Certificate signed once with ML-DSA-87 (FIPS 204, NIST Level 5), replacing per-operation signing with sub-microsecond boundary checks at 4.7M ops/sec; (2) a six-check Boundary Engine enforcing hard constraints, rate limits, and escalation triggers with zero cryptographic overhead on the critical path; (3) a push-based Revocation Protocol propagating invalidation within one second. A three-tier SHA-256 Responsibility Chain provides tamper-evident audit logging. All five security theorems are machine-verified via Tamarin Prover under the Dolev-Yao model. We validate AITH through five rounds of multi-model adversarial auditing, resolving 12 vulnerabilities across four severity layers. Simulation of 100,000 operations shows 79.5% autonomous execution, 6.1% human escalation, and 14.4% blocked.