# Verification methods for international AI agreements

arXiv: https://arxiv.org/abs/2408.16074 · HTML: https://mlsanity.com/paper/2408.16074/

## 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 (most cited first, 12 of 12)

- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Model evaluation for extreme risks](https://mlsanity.com/paper/2305.15324/) (2023)
- [Evaluating Frontier Models for Dangerous Capabilities](https://mlsanity.com/paper/2403.13793/) (2024)
- [Black-Box Access is Insufficient for Rigorous AI Audits](https://mlsanity.com/paper/2401.14446/) (2024)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)
- [Computing Power and the Governance of Artificial Intelligence](https://mlsanity.com/paper/2402.08797/) (2024)
- [What does it take to catch a Chinchilla? Verifying Rules on Large-Scale Neural Network Training via Compute Monitoring](https://mlsanity.com/paper/2303.11341/) (2023)
- [Towards Publicly Accountable Frontier LLMs: Building an External Scrutiny Ecosystem under the ASPIRE Framework](https://mlsanity.com/paper/2311.14711/) (2023)
- [International Governance of Civilian AI: A Jurisdictional Certification Approach](https://mlsanity.com/paper/2308.15514/) (2023)
- [Nuclear Arms Control Verification and Lessons for AI Treaties](https://mlsanity.com/paper/2304.04123/) (2023)
- [Affirmative safety: An approach to risk management for high-risk AI](https://mlsanity.com/paper/2406.15371/) (2024)
- [AI Emergency Preparedness: Examining the federal government's ability to detect and respond to AI-related national security threats](https://mlsanity.com/paper/2407.17347/) (2024)

## Built on by (most cited first, 10 of 10)

- [Distributional AGI Safety](https://mlsanity.com/paper/2512.16856/) (2025)
- [Superintelligence Strategy: Expert Version](https://mlsanity.com/paper/2503.05628/) (2025)
- [International Agreements on AI Safety: Review and Recommendations for a Conditional AI Safety Treaty](https://mlsanity.com/paper/2503.18956/) (2025)
- [Bit-Exact AI Inference Verification Without Performance Tradeoffs](https://mlsanity.com/paper/2606.00279/) (2026)
- [Technical Requirements for Halting Dangerous AI Activities](https://mlsanity.com/paper/2507.09801/) (2025)
- [Against racing to AGI: Cooperation, deterrence, and catastrophic risks](https://mlsanity.com/paper/2507.21839/) (2025)
- [Internal Deployment Gaps in AI Regulation](https://mlsanity.com/paper/2601.08005/) (2026)
- [Policy-Driven AI in Dataspaces: Taxonomy, Explainability, and Pathways for Compliant Innovation](https://mlsanity.com/paper/2507.20014/) (2025)
- [Does Distributed Training Undermine Compute Governance?](https://mlsanity.com/paper/2605.29359/) (2026)
- [Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance](https://mlsanity.com/paper/2609.10105/) (2026)

## 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.