SUDP: Secret-Use Delegation Protocol for Agentic Systems

• URL: http://arxiv.org/abs/2604.24920v2
• Date: Fri, 01 May 2026 04:48:19 GMT
• Title: SUDP: Secret-Use Delegation Protocol for Agentic Systems
• Abstract summary: Agentic systems increasingly act with user secrets for APIs, messaging platforms, and cloud services.<n>Existing defenses cover adjacent pieces such as secret storage, scoped delegation, sender-constrained tokens, and runtime monitoring.<n>We formalize this problem as Agent Secret Use (ASU)
• Score: 2.158253409290015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic systems increasingly act with user secrets for APIs, messaging platforms, and cloud services. Today's bearer-secret interfaces implement authorization by exposure: enabling action often means placing a reusable secret, or a reusable artifact derived from it, within a model-steerable boundary, so a transient prompt-injection or tool-side compromise becomes durable account compromise. Existing defenses cover adjacent pieces such as secret storage, scoped delegation, sender-constrained tokens, and runtime monitoring, but leave the combined agentic obligation without a common specification: an untrusted autonomous requester should be able to cause a user-authorized secret-backed operation without exposing reusable authority to the requester. We formalize this problem as Agent Secret Use (ASU). From ASU we derive a security-property taxonomy that separates the problem's structural obligations from the realization-level robustness conditions any concrete construction must establish, enabling principled comparison of existing agentic-secret defenses against a problem-grounded specification. We propose the Secret-Use Delegation Protocol (SUDP), a three-role protocol realizing ASU: a requester proposes a canonical operation; the user authorizes it with a fresh authenticator-backed grant; and a custodian redeems the grant once to perform the bounded use, so reusable authority never crosses the requester boundary. We specialize SUDP for agentic deployments: agents propose operations; they do not retrieve secrets. Under explicit assumptions, we show that SUDP satisfies the ASU requirements: authorization is verifiable, operation-bound, and single-use. SUDP also provides storage confidentiality and wrapping-epoch key isolation under stated sealing and erasure assumptions; plaintext-level forward secrecy of the underlying secret additionally requires the environment to rotate and revoke it.

Related papers

• Toward cryptographically verifiable authorization for autonomous AI agents: A security hypothesis, preliminary formal model, and proof-of-concept implementation [0.0]
  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)
  arXiv  Detail & Related papers  (2026-07-23T13:55:02Z)
• Threshold Authorization Without Threshold Signatures: Signature-Agnostic MPC Custody [0.0]
  We present a dual-gate architecture that separates member authentication from threshold authorization.<n>The architecture can be deployed wherever the asset-control path supports programmable verification.
  arXiv  Detail & Related papers  (2026-07-09T08:20:45Z)
• GoodDiffusion: Proactive Copyright Protection for Diffusion Bridge Models via Learnable Sample-specific Signatures [88.63093209858387]
  We propose GoodDiffusion, inspired by backdoor mechanisms, to enforce model-level use-time control.<n>GoodDiffusion preserves high-quality generation for authorized queries carrying valid signatures, yet refuses to generate for unauthorized inputs.<n>To strengthen security, we introduce a Learnable Signature Network (LSN) that assigns sample-specific signatures conditioned on each input.
  arXiv  Detail & Related papers  (2026-06-29T04:07:09Z)
• Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure [2.124730017640531]
  Sovereign Assurance Boundary is a certificate-bound runtime admission layer for autonomous execution authority.<n>We detail the airlock-broker architecture, formalize its admission and revocation invariants, and report preliminary feasibility measurements from a Go prototype.
  arXiv  Detail & Related papers  (2026-06-10T03:49:57Z)
• PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments [59.07829883257003]
  Built on five multi-room apartments, PRISM structures 300 human-verified tasks into three capability tiers.<n>PRISM exposes an agent-agnostic executable action API that allows arbitrary agents to be evaluated end-to-end.
  arXiv  Detail & Related papers  (2026-05-12T04:59:47Z)
• Write-Domain Separation and Non-Custodial Enforcement: A Structural Impossibility in Account-Based Ledgers, with a Commitment-Based Construction [0.0]
  We ask a structural question about ledger access control.<n>Can a protocol enforce the future disposition of an asset without taking custody and without requiring the owner's cooperation at enforcement time?<n>We formalize the target as Non-Custodial Enforced Encumbrance (NCEE), a four-property specification covering self-custody, transition restriction, irrevocability, and permissionless enforcement.
  arXiv  Detail & Related papers  (2026-05-02T02:59:55Z)
• CapSeal: Capability-Sealed Secret Mediation for Secure Agent Execution [1.9473631530390483]
  CapSeal is a capability-sealed secret mediation architecture that replaces direct secret access with constrained invocations through a local trusted broker.<n>We describe a Rust prototype integrated with an MCP-facing adapter, formulate conditional security goals for non-disclosure, constrained use, replay resistance, and auditability.
  arXiv  Detail & Related papers  (2026-04-18T00:23:32Z)
• Condition-Triggered Cryptographic Asset Control via Dormant Authorization Paths [1.7429038786735553]
  Control of encrypted digital assets is traditionally equated with permanent possession of private keys.<n>We introduce Condition-Triggered Dormant Authorization Paths (CT-DAP)<n>CT-DAP is a cryptographic asset control method built on destructible authorization factors.
  arXiv  Detail & Related papers  (2026-03-09T03:57:06Z)
• RAIN: Secure and Robust Aggregation under Shuffle Model of Differential Privacy [46.52109845749167]
  We present Robust Aggregation in Noise (RAIN), a framework that reconciles privacy, robustness, and verifiability under Shuffle-DP.<n>RAIN adopts sign-space aggregation to robustly measure update consistency and limit malicious influence under noise and anonymization.<n>We show that RAIN maintains strong privacy guarantees under Shuffle-DP and remains robust to poisoning attacks with negligible degradation in accuracy and convergence.
  arXiv  Detail & Related papers  (2026-03-03T15:41:54Z)
• Multi-Agent-Driven Cognitive Secure Communications in Satellite-Terrestrial Networks [58.70163955407538]
  Malicious eavesdroppers pose a serious threat to private information via satellite-terrestrial networks (STNs)<n>We propose a cognitive secure communication framework driven by multiple agents that coordinates spectrum scheduling and protection through real-time sensing.<n>We exploit generative adversarial networks to produce adversarial matrices, and employ learning-aided power control to set real and adversarial signal powers for protection layer.
  arXiv  Detail & Related papers  (2026-01-06T10:30:41Z)
• A Privacy Protocol Using Ephemeral Intermediaries and a Rank-Deficient Matrix Power Function (RDMPF) [0.0]
  This paper presents a private transfer architecture for the Internet Computer (ICP)<n>It decouples deposit and retrieval through two short-lived intermediaries, with sealed storage and attested by an ephemeral witness.<n>The protocol uses a non-interactive RDMPF-based encapsulation to derive per-transfer transport keys.
  arXiv  Detail & Related papers  (2025-12-29T15:19:09Z)
• 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)
• LLM Agents Should Employ Security Principles [60.03651084139836]
  This paper argues that the well-established design principles in information security should be employed when deploying Large Language Model (LLM) agents at scale.<n>We introduce AgentSandbox, a conceptual framework embedding these security principles to provide safeguards throughout an agent's life-cycle.
  arXiv  Detail & Related papers  (2025-05-29T21:39:08Z)
• CoTGuard: Using Chain-of-Thought Triggering for Copyright Protection in Multi-Agent LLM Systems [55.57181090183713]
  We introduce CoTGuard, a novel framework for copyright protection that leverages trigger-based detection within Chain-of-Thought reasoning.<n>Specifically, we can activate specific CoT segments and monitor intermediate reasoning steps for unauthorized content reproduction by embedding specific trigger queries into agent prompts.<n>This approach enables fine-grained, interpretable detection of copyright violations in collaborative agent scenarios.
  arXiv  Detail & Related papers  (2025-05-26T01:42:37Z)
• A Novel Zero-Trust Identity Framework for Agentic AI: Decentralized Authentication and Fine-Grained Access Control [7.228060525494563]
  This paper posits the imperative for a novel Agentic AI IAM framework.<n>We propose a comprehensive framework built upon rich, verifiable Agent Identities (IDs)<n>We also explore how Zero-Knowledge Proofs (ZKPs) enable privacy-preserving attribute disclosure and verifiable policy compliance.
  arXiv  Detail & Related papers  (2025-05-25T20:21:55Z)
• Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoning [58.57194301645823]
  Large language models (LLMs) are increasingly integrated into real-world personalized applications.<n>The valuable and often proprietary nature of the knowledge bases used in RAG introduces the risk of unauthorized usage by adversaries.<n>Existing methods that can be generalized as watermarking techniques to protect these knowledge bases typically involve poisoning or backdoor attacks.<n>We propose name for harmless' copyright protection of knowledge bases.
  arXiv  Detail & Related papers  (2025-02-10T09:15:56Z)
• Balancing Confidentiality and Transparency for Blockchain-based Process-Aware Information Systems [43.253676241213626]
  We propose an architecture for blockchain-based PAISs to preserve confidentiality and transparency.<n>Smart contracts enact, enforce and store public interactions, while attribute-based encryption techniques are adopted to specify access grants to confidential information.<n>We assess the security of our solution through a systematic threat model analysis and evaluate its practical feasibility.
  arXiv  Detail & Related papers  (2024-12-07T20:18:36Z)

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.