GPU Fingerprinting for Location Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tee, Wayne, Happel, Jonathan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910278393790464
author Tee, Wayne
Happel, Jonathan
author_facet Tee, Wayne
Happel, Jonathan
contents Robust governance of GPU chips is important for mitigating risks from unauthorized development of advanced AI models. Current methods for monitoring chip location rely on ping-based protocols backed by cryptographic keys stored on-chip. However, these keys can potentially be extracted by adversaries with physical access, compromising the location verification protocol. We address this vulnerability by proposing the use of hardware fingerprints rather than keys to identify GPUs during location verification. In addition, we develop a proof-of-concept GPU fingerprinting methodology that achieves up to 100% re-identification accuracy in small-scale tests.
format Preprint
id arxiv_https___arxiv_org_abs_2605_01930
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GPU Fingerprinting for Location Verification
Tee, Wayne
Happel, Jonathan
Cryptography and Security
Robust governance of GPU chips is important for mitigating risks from unauthorized development of advanced AI models. Current methods for monitoring chip location rely on ping-based protocols backed by cryptographic keys stored on-chip. However, these keys can potentially be extracted by adversaries with physical access, compromising the location verification protocol. We address this vulnerability by proposing the use of hardware fingerprints rather than keys to identify GPUs during location verification. In addition, we develop a proof-of-concept GPU fingerprinting methodology that achieves up to 100% re-identification accuracy in small-scale tests.
title GPU Fingerprinting for Location Verification
topic Cryptography and Security
url https://arxiv.org/abs/2605.01930