# Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance

arXiv: https://arxiv.org/abs/2610.07476 · HTML: https://mlsanity.com/paper/2610.07476/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 37 references that are in the map.
- First posted on arXiv 5 Oct 2026.

## Builds on (most cited first, 12 of 12)

- [Open Problems in Technical AI Governance](https://mlsanity.com/paper/2407.14981/) (2024)
- [Computing Power and the Governance of Artificial Intelligence](https://mlsanity.com/paper/2402.08797/) (2024)
- [International AI Safety Report 2026](https://mlsanity.com/paper/2602.21012/) (2026)
- [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)
- [Training Compute Thresholds: Features and Functions in AI Regulation](https://mlsanity.com/paper/2405.10799/) (2024)
- [Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment](https://mlsanity.com/paper/2507.15916/) (2025)
- [POLCA: Power Oversubscription in LLM Cloud Providers](https://mlsanity.com/paper/2308.12908/) (2023)
- [Power Stabilization for AI Training Datacenters](https://mlsanity.com/paper/2508.14318/) (2025)
- [Hardware-Enabled Mechanisms for Verifying Responsible AI Development](https://mlsanity.com/paper/2505.03742/) (2025)
- [Timing and Memory Telemetry on GPUs for AI Governance](https://mlsanity.com/paper/2602.09369/) (2026)
- [Hardware-Level Governance of AI Compute: A Feasibility Taxonomy for Regulatory Compliance and Treaty Verification](https://mlsanity.com/paper/2604.04712/) (2026)
- [Detecting Hidden ML Training With Zero-Overhead Telemetry](https://mlsanity.com/paper/2606.19262/) (2026)

## Abstract (arXiv)

Frontier AI treaties or agreements on limiting computation require external verification; an external auditor must be able to confirm how much computation actually ran and that parties are adhering to the agreement. Analogue, off-chip measurements such as power draw provide an information channel for verification. It is unknown how well these analogue channels can constrain computation against an adversary who actively tries to subvert the audit. We derive a closed form for β, the largest hidden computation a power trace cannot exclude, as a fraction of the declared machine capacity. Measurements on NVIDIA A100 GPUs constrain β = 1.16 in the worst case, while adversarial matched-energy strategies are shown to hide at least β = 0.41 of compute. Analogue power measurements alone therefore constrain compute weakly. Additional restrictions granted by the threat model, such as the ability of the verifier to re-execute the declared work at an observed operating point, let the verifier push β down to 0.059 in the maximally restricted case. This gives a quantitative estimate of what analogue measurements can contribute to compute verification.