mlsanityData to 7 Oct 2026

Proof-of-Guardrail in AI Agents and What (Not) to Trust from It

arXiv 2603.05786 ↗First posted 6 Mar 2026cs.CR cs.AI cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

As AI agents become widely deployed as online services, users often rely on an agent developer's claim about how safety is enforced, which introduces a threat where safety measures are falsely advertised. To address the threat, we propose proof-of-guardrail, a system that enables developers to provide cryptographic proof that a response is generated after a specific open-source guardrail. To generate proof, the developer runs the agent and guardrail inside a Trusted Execution Environment (TEE), which produces a TEE-signed attestation of guardrail code execution verifiable by any user offline. We implement proof-of-guardrail for OpenClaw agents and evaluate latency overhead and deployment cost. Proof-of-guardrail ensures integrity of guardrail execution while keeping the developer's agent private, but we also highlight a risk of deception about safety, for example, when malicious developers actively jailbreak the guardrail. Code and demo video: https://github.com/SaharaLabsAI/Verifiable-ClawGuard

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 19 of its 30 references that are in the map. First posted on arXiv 6 Mar 2026.

Builds on

19 of 30 references.

References · 19

  1. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,124
  2. 2023FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarioscited by 247
  3. 2023ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversationcited by 224
  4. 2025Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teamingcited by 172
  5. 2025Agentic Misalignment: How LLMs Could Be Insider Threatscited by 136
  6. 2025LlamaFirewall: An open source guardrail system for building secure AI agentscited by 114
  7. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 101
  8. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  9. 2025OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safetycited by 71
  10. 2026Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreakscited by 36
  11. 2025Are You Getting What You Pay For? Auditing Model Substitution in LLM APIscited by 35
  12. 2018Efficient Deep Learning on Multi-Source Private Datacited by 16
7 more
  1. 2024Loki: An Open-Source Tool for Fact Verificationcited by 16
  2. 2024Verifiable evaluations of machine learning models using zkSNARKscited by 14
  3. 2020Secure Collaborative Training and Inference for XGBoostcited by 9
  4. 2024Laminator: Verifiable ML Property Cards using Hardware-assisted Attestationscited by 9
  5. 2025Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environmentscited by 8
  6. 2020Golden Grain: Building a Secure and Decentralized Model Marketplace for MLaaScited by 6
  7. 2026PAL*M: Property Attestation for Large Generative Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agentscited by 12
  2. 2026From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AIcited by 7
  3. 2026BraveGuard: From Open-World Threats to Safer Computer-Use Agentscited by 4
  4. 2026Beyond Task Success: An Evidence-Synthesis Framework for Evaluating, Governing, and Orchestrating Agentic AIcited by 2