Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation

• URL: http://arxiv.org/abs/2607.21325v1
• Date: Thu, 23 Jul 2026 13:55:02 GMT
• Title: Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation
• Abstract summary: This paper hypothesizes that agent authorization can be formalized as a cryptographically verifiable relation.<n>We introduce a preliminary formal abstraction for Cryptographically Verifiable Agent Authorization (CVA)
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Autonomous AI agents increasingly execute actions, invoke tools, and operate on protected resources with limited human oversight. Existing authentication and authorization mechanisms establish identity and delegate authority, but do not inherently provide cryptographic evidence that a concrete request issued by a specific agent satisfies the applicable policy in a specific execution context. This paper hypothesizes that agent authorization can be formalized as a cryptographically verifiable relation, denoted $R_{CVA}$, that jointly binds an agent principal, a concrete authorization request, an execution context, and the satisfaction of an applicable policy, while selectively preserving the confidentiality of private authorization attributes. We introduce a preliminary formal abstraction for Cryptographically Verifiable Agent Authorization (CVA), define a compact set of candidate security properties including authorization soundness, principal binding, request binding, policy binding, and replay resistance, and provide an executable zero-knowledge proof of concept that instantiates selected elements of the model over a Groth16 zk-SNARK construction. We further identify and formalize the structural separation among identity binding, authorization-request binding, and runtime execution binding as a central open problem in the design of secure agentic systems (a distinction {not explicitly addressed by} current agentic security frameworks) and present a falsifiable research agenda for its resolution.

Related papers

• Mandato: Protocol-Level Enforcement of Digitally Signed Mandates on AI Agent Actions with Cryptographically Chained Audit Trails [0.0]
  We present Mandato, a governance proxy that enforces digitally signed mandates on agent actions at the protocol level.<n>A mandate is a machine-readable, cryptographically signed authorization artifact specifying which tools an agent may invoke.<n>We describe the implementation status of the reference system and a quantitative evaluation plan covering enforcement overhead, audit completeness, and tamper-evidence verification cost.
  arXiv  Detail & Related papers  (2026-08-14T08:33:43Z)
• Behavioral Governance for Autonomous AI Agents: The AgentBound Framework [2.4469484645516832]
  We present AgentBound, a runtime governance framework that provides verifiable behavioral oversight for autonomous AI agents.<n>AgentBound evaluates each proposed action using three independent authorities: delegated authorization, owner-signed behavioral constitutions, and site action contracts.<n>AgentBound generates cryptographically verifiable governance receipts that bind every action to the exact delegation, policy, and semantic artifacts governing the decision.
  arXiv  Detail & Related papers  (2026-06-29T23:12:06Z)
• Overlaying Governance: A Compositional Authorization Framework for Delegation and Scope in Agentic AI [5.459755757192724]
  This paper proposes a compositional governance framework for agentic AI systems.<n>We define types of delegation and their permissions and accountability implications.<n>It provides a formal yet practical foundation for accountable authorization in agentic AI systems.
  arXiv  Detail & Related papers  (2026-06-02T11:39:39Z)
• Provably Secure Agent Guardrail [89.79561918065122]
  Existing defense architectures rely on empirical semantic guardrails and probabilistic large model adjudicators.<n>This paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning.
  arXiv  Detail & Related papers  (2026-05-28T02:12:41Z)
• Verifiable Agentic Infrastructure: Proof-Derived Authorization for Sovereign AI Systems [2.124730017640531]
  We introduce a verification framework for governed mutation systems that computes execution authority from structured artifacts.<n>DTF provides an infrastructure foundation for making agentic execution governable, auditable, and bounded in sovereign AI deployments.
  arXiv  Detail & Related papers  (2026-05-13T17:58:52Z)
• Digital Identity for Agentic Systems: Toward a Portable Authorization Standard for Autonomous Agents [0.0]
  This paper analyzes representative enterprise use cases in insurance claims processing and supply chain integrity.<n>It proposes a portable authorization model for autonomous agents based on issuer-authored authorization payloads.
  arXiv  Detail & Related papers  (2026-05-12T04:04:34Z)
• The Authorization-Execution Gap Is a Major Safety and Security Problem in Open-World Agents [111.54911637435269]
  The Authorization-Execution Gap (AEG) is a major safety and security problem in open-world agents.<n>The AEG is the divergence between what a principal intends to authorize and what an open-world agent ultimately executes.
  arXiv  Detail & Related papers  (2026-05-10T04:05:31Z)
• Verification of Robust Properties for Access Control Policies [51.736723807086385]
  Existing methods for verifying access control policies require the policy to be complete and fully determined before verification can proceed.<n>We introduce robust property verification: the problem of determining what a policy's structure commits it to regardless of how pending decisions are resolved and regardless of subsequent extension.<n>We show that despite quantifying universally over all possible policy extensions the judgment reduces to proof search in a second-order logic programming language.
  arXiv  Detail & Related papers  (2026-03-13T17:14:38Z)
• Authorize-on-Demand: Dynamic Authorization with Legality-Aware Intellectual Property Protection for VLMs [70.09137776277994]
  AoD-IP is a framework that supports authorize-on-demand and legality-aware assessment.<n>AoD-IP maintains strong authorized-domain performance and reliable unauthorized detection.
  arXiv  Detail & Related papers  (2026-03-05T07:36:07Z)
• Interoperable Architecture for Digital Identity Delegation for AI Agents with Blockchain Integration [0.0]
  We introduce a unified framework that enables bounded, auditable, and least-privilege delegation across heterogeneous identity ecosystems.<n>The framework includes four key elements: Delegation Grants (DGs), first-class authorization artefacts that encode revocable transfers of authority with enforced scope reduction.<n>It also includes a layered reference architecture that separates trust anchoring, credential and proof validation, policy evaluation, and protocol mediation via a Trust Gateway.
  arXiv  Detail & Related papers  (2026-01-21T13:29:23Z)
• Binding Agent ID: Unleashing the Power of AI Agents with accountability and credibility [46.323590135279126]
  BAID (Binding Agent ID) is a comprehensive identity infrastructure establishing verifiable user-code binding.<n>We implement and evaluate a complete prototype system, demonstrating the practical feasibility of blockchain-based identity management and zkVM-based authentication protocol.
  arXiv  Detail & Related papers  (2025-12-19T13:01:54Z)
• Combining Decentralized IDentifiers with Proof of Membership to Enable Trust in IoT Networks [44.99833362998488]
  The paper proposes and discusses an alternative (mutual) authentication process for IoT nodes under the same administration domain. The main idea is to combine the Decentralized IDentifier (DID)-based verification of private key ownership with the verification of a proof that the DID belongs to an evolving trusted set.
  arXiv  Detail & Related papers  (2023-10-12T09:33:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.