A General Framework for Data-Use Auditing of ML Models
Abstract
Auditing the use of data in training machine-learning (ML) models is an increasingly pressing challenge, as myriad ML practitioners routinely leverage the effort of content creators to train models without their permission. In this paper, we propose a general method to audit an ML model for the use of a data-owner's data in training, without prior knowledge of the ML task for which the data might be used. Our method leverages any existing black-box membership inference method, together with a sequential hypothesis test of our own design, to detect data use with a quantifiable, tunable false-detection rate. We show the effectiveness of our proposed framework by applying it to audit data use in two types of ML models, namely image classifiers and foundation models.
Cite
@article{arxiv.2407.15100,
title = {A General Framework for Data-Use Auditing of ML Models},
author = {Zonghao Huang and Neil Zhenqiang Gong and Michael K. Reiter},
journal= {arXiv preprint arXiv:2407.15100},
year = {2025}
}
Comments
The full paper of "A General Framework for Data-Use Auditing of ML Models" accepted by ACM CCS 2024