Metraipolis › archive › dc_4e5f95d5af2a

Detecting AI Training in Datacentre Power — arXiv:2610.30182

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.30182
License (as archived)
CC0-1.0
Archived
2026-10-23T15:14:43.286Z
SHA-256 of the archived text
bd119de65d25a3dad35158d527db5eed9e38e2e309cd952b715d7112841f91c4
Stable URL of this page
https://metraipolis.com/documento/dc_4e5f95d5af2a

How to cite

Detecting AI Training in Datacentre Power — arXiv:2610.30182 — arXiv (en), https://arxiv.org/abs/2610.30182 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e5f95d5af2a (Metraipolis archive dc_4e5f95d5af2a, sha256 bd119de65d25a3dad35158d527db5eed9e38e2e309cd952b715d7112841f91c4)
BibTeX
@misc{dc4e5f95d5af2a,
  title = {Detecting AI Training in Datacentre Power — arXiv:2610.30182},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30182},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e5f95d5af2a; sha256 bd119de65d25a3dad35158d527db5eed9e38e2e309cd952b715d7112841f91c4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30182. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI governance agreements require methods to detect large model training runs on a monitored computing cluster, without trusting the operator. We develop a method to detect synchronous model training in facility-level power by Viterbi tracking of the wandering iteration cadence. On simulated datacentre power, when the operator makes no attempt to hide, the Viterbi tracker detects at least $96\%$ of training runs against a declared inference workload, at a $1\%$ false-alarm rate and within $0.04$ of the Neyman--Pearson optimum, given a meter that samples at $2$ Hz or faster. Of eight adversarial strategies an operator might use to hide, only extreme variation of the work per iteration evades the tracker. Its strongest form hides training in up to $73\%$ of five-minute observations, but over a day at least $87\%$ of such runs are still caught, at a $0.1\%$ false-alarm rate per run. This adversarial strategy costs no throughput, but in small-scale training the operator needs $93$--$267\%$ more compute to reach the same loss. A modest passive meter is sufficient to make hidden training both detectable and expensive, which makes power metering a promising part of compute verification that does not depend on trusting the operator.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.30182 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-23T15:09:08.485Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).