# Mechanisms to Verify International Agreements About AI Development

arXiv: https://arxiv.org/abs/2506.15867 · HTML: https://mlsanity.com/paper/2506.15867/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2025.

## Built on by (most cited first, 9 of 9)

- [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)
- [Compute Requirements for Algorithmic Innovation in Frontier AI Models](https://mlsanity.com/paper/2507.10618/) (2025)
- [Against racing to AGI: Cooperation, deterrence, and catastrophic risks](https://mlsanity.com/paper/2507.21839/) (2025)
- [Password-Activated Shutdown Protocols for Misaligned Frontier Agents](https://mlsanity.com/paper/2512.03089/) (2025)
- [International Agreements to Limit Frontier AI: Objectives and Exit](https://mlsanity.com/paper/2607.16224/) (2026)
- [Privacy-Preserving AI Verification via Minimal Information Disclosure](https://mlsanity.com/paper/2608.02774/) (2026)
- [The Closing Window: How Governments Could Lose Their Ability to Restrain Advanced AI](https://mlsanity.com/paper/2608.05173/) (2026)
- [Workload Identification with Physical Side Channels for AI Governance](https://mlsanity.com/paper/2609.00309/) (2026)

## Abstract (arXiv)

International agreements about AI development may be required to reduce catastrophic risks from advanced AI systems. However, agreements about such a high-stakes technology must be backed by verification mechanisms--processes or tools that give one party greater confidence that another is following the agreed-upon rules, typically by detecting violations. This report gives an overview of potential verification approaches for three example policy goals, aiming to demonstrate how countries could practically verify claims about each other's AI development and deployment. The focus is on international agreements and state-involved AI development, but these approaches could also be applied to domestic regulation of companies. While many of the ideal solutions for verification are not yet technologically feasible, we emphasize that increased access (e.g., physical inspections of data centers) can often substitute for these technical approaches. Therefore, we remain hopeful that significant political will could enable ambitious international coordination, with strong verification mechanisms, to reduce catastrophic AI risks.