Embedded Off-Switches for AI Compute

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autor principal: Petrie, James
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909778872107008
author Petrie, James
author_facet Petrie, James
contents To address the risks of increasingly capable AI systems, we introduce a hardware-level off-switch that embeds thousands of independent "security blocks" in each AI accelerator. This massively redundant architecture is designed to prevent unauthorized chip use, even against sophisticated physical attacks. Our main security block design uses public key cryptography to check the authenticity of authorization licenses, and randomly generated nonces to prevent replay attacks. We evaluate attack vectors and present additional security block variants that could be added for greater robustness. Security blocks can be built with standard circuit components, ensuring compatibility with existing semiconductor manufacturing processes. With embedded security blocks, the next generation of AI accelerators could be more robustly defended against dangerous misuse.
format Preprint
id arxiv_https___arxiv_org_abs_2509_07637
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Embedded Off-Switches for AI Compute
Petrie, James
Cryptography and Security
To address the risks of increasingly capable AI systems, we introduce a hardware-level off-switch that embeds thousands of independent "security blocks" in each AI accelerator. This massively redundant architecture is designed to prevent unauthorized chip use, even against sophisticated physical attacks. Our main security block design uses public key cryptography to check the authenticity of authorization licenses, and randomly generated nonces to prevent replay attacks. We evaluate attack vectors and present additional security block variants that could be added for greater robustness. Security blocks can be built with standard circuit components, ensuring compatibility with existing semiconductor manufacturing processes. With embedded security blocks, the next generation of AI accelerators could be more robustly defended against dangerous misuse.
title Embedded Off-Switches for AI Compute
topic Cryptography and Security
url https://arxiv.org/abs/2509.07637