Metraipolis › archive › dc_53eb2239fb5b
arXiv 2610.07476: Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance
- Source
- Metraipolis archive
- Original
- https://arxiv.org/abs/2610.07476
- License (as archived)
- CC-BY-4.0
- Archived
- 2026-10-07T20:18:23.821Z
- SHA-256 of the archived text
ff0c9119fdeb9d1a1d620023feb1761008be4196e4c7a6a3b8fe67970b2a0664- Stable URL of this page
https://metraipolis.com/documento/dc_53eb2239fb5b
How to cite
arXiv 2610.07476: Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance — Metraipolis archive, https://arxiv.org/abs/2610.07476 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_53eb2239fb5b (Metraipolis archive dc_53eb2239fb5b, sha256 ff0c9119fdeb9d1a1d620023feb1761008be4196e4c7a6a3b8fe67970b2a0664)
BibTeX
@misc{dc53eb2239fb5b,
title = {arXiv 2610.07476: Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance},
howpublished = {Metraipolis archive},
url = {https://arxiv.org/abs/2610.07476},
note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_53eb2239fb5b; sha256 ff0c9119fdeb9d1a1d620023feb1761008be4196e4c7a6a3b8fe67970b2a0664},
year = {2026}
}Archived text
Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.07476. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 $\beta$, the largest hidden computation a power trace cannot exclude, as a fraction of the declared machine capacity. Measurements on NVIDIA A100 GPUs constrain $\beta = 1.16$ in the worst case, while adversarial matched-energy strategies are shown to hide at least $\beta = 0.41$ 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 $\beta$ down to $0.059$ in the maximally restricted case. This gives a quantitative estimate of what analogue measurements can contribute to compute verification. Articolo: «Can Power Draw Constrain Covert Compute? Limits of Analogue Verification for AI Governance» — Kimpson, Tom; Baker, Mauricio; Graham, Emlyn (2026-10-05), arXiv:2610.07476, categoria cs.CY (informatica e società). Fonte: https://arxiv.org/abs/2610.07476 Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv. Consultato il 2026-10-07T20:18:12Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.