Salvato in:
Dettagli Bibliografici
Autori principali: Petrie, James, Aarne, Onni, Ammann, Nora, Dalrymple, David
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.15093
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912436955643904
author Petrie, James
Aarne, Onni
Ammann, Nora
Dalrymple, David
author_facet Petrie, James
Aarne, Onni
Ammann, Nora
Dalrymple, David
contents As artificial intelligence systems become increasingly powerful, they pose growing risks to international security, creating urgent coordination challenges that current governance approaches struggle to address without compromising sensitive information or national security. We propose flexible hardware-enabled guarantees (flexHEGs), that could be integrated with AI accelerators to enable trustworthy, privacy-preserving verification and enforcement of claims about AI development. FlexHEGs consist of an auditable guarantee processor that monitors accelerator usage and a secure enclosure providing physical tamper protection. The system would be fully open source with flexible, updateable verification capabilities. FlexHEGs could enable diverse governance mechanisms including privacy-preserving model evaluations, controlled deployment, compute limits for training, and automated safety protocol enforcement. In this first part of a three part series, we provide a comprehensive introduction of the flexHEG system, including an overview of the governance and security capabilities it offers, its potential development and adoption paths, and the remaining challenges and limitations it faces. While technically challenging, flexHEGs offer an approach to address emerging regulatory and international security challenges in frontier AI development.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Flexible Hardware-Enabled Guarantees for AI Compute
Petrie, James
Aarne, Onni
Ammann, Nora
Dalrymple, David
Cryptography and Security
As artificial intelligence systems become increasingly powerful, they pose growing risks to international security, creating urgent coordination challenges that current governance approaches struggle to address without compromising sensitive information or national security. We propose flexible hardware-enabled guarantees (flexHEGs), that could be integrated with AI accelerators to enable trustworthy, privacy-preserving verification and enforcement of claims about AI development. FlexHEGs consist of an auditable guarantee processor that monitors accelerator usage and a secure enclosure providing physical tamper protection. The system would be fully open source with flexible, updateable verification capabilities. FlexHEGs could enable diverse governance mechanisms including privacy-preserving model evaluations, controlled deployment, compute limits for training, and automated safety protocol enforcement. In this first part of a three part series, we provide a comprehensive introduction of the flexHEG system, including an overview of the governance and security capabilities it offers, its potential development and adoption paths, and the remaining challenges and limitations it faces. While technically challenging, flexHEGs offer an approach to address emerging regulatory and international security challenges in frontier AI development.
title Flexible Hardware-Enabled Guarantees for AI Compute
topic Cryptography and Security
url https://arxiv.org/abs/2506.15093