mlsanityData to 14 Oct 2026

Verification methods for international AI agreements

arXiv 2408.16074 ↗First posted 28 Aug 2024cs.CY cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

What techniques can be used to verify compliance with international agreements about advanced AI development? In this paper, we examine 10 verification methods that could detect two types of potential violations: unauthorized AI training (e.g., training runs above a certain FLOP threshold) and unauthorized data centers. We divide the verification methods into three categories: (a) national technical means (methods requiring minimal or no access from suspected non-compliant nations), (b) access-dependent methods (methods that require approval from the nation suspected of unauthorized activities), and (c) hardware-dependent methods (methods that require rules around advanced hardware). For each verification method, we provide a description, historical precedents, and possible evasion techniques. We conclude by offering recommendations for future work related to the verification and enforcement of international AI governance agreements.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 12 of its 54 references that are in the map. First posted on arXiv 28 Aug 2024.

Builds on

12 of 54 references.

References · 12

  1. 2020Artificial Intelligence, Values and Alignmentcited by 448
  2. 2023Model evaluation for extreme riskscited by 177
  3. 2024Evaluating Frontier Models for Dangerous Capabilitiescited by 128
  4. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 126
  5. 2021Compute and Energy Consumption Trends in Deep Learning Inferencecited by 61
  6. 2024Computing Power and the Governance of Artificial Intelligencecited by 40
  7. 2023What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoringcited by 21
  8. 2023Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Frameworkcited by 11
  9. 2023International Governance of Civilian AI: A Jurisdictional Certification Approachcited by 8
  10. 2023Nuclear Arms Control Verification and Lessons for AI Treatiescited by 6
  11. 2024Affirmative safety: An approach to risk management for high-risk AIcited by 3
  12. 2024AI Emergency Preparedness: Examining the federal government's ability to detect and respond to AI-related national security threatscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 4.

10 papers.

  1. 2025Distributional AGI Safetycited by 12
  2. 2025Superintelligence Strategy: Expert Versioncited by 7
  3. 2025International Agreements on AI Safety: Review and Recommendations for a Conditional AI Safety Treatycited by 4
  4. 2026Bit-Exact AI Inference Verification Without Performance Tradeoffscited by 4
  5. 2025Technical Requirements for Halting Dangerous AI Activitiescited by 2
  6. 2025Against racing to AGI: Cooperation, deterrence, and catastrophic riskscited by 2
  7. 2026Internal Deployment Gaps in AI Regulationcited by 2
  8. 2025Policy-Driven AI in Dataspaces: Taxonomy, Explainability, and Pathways for Compliant Innovationcited by 0
  9. 2026Does Distributed Training Undermine Compute Governance?cited by 0
  10. 2026Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governancecited by 0