English

A General Framework for Data-Use Auditing of ML Models

Cryptography and Security 2025-01-28 v3 Machine Learning

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.

Keywords

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

R2 v1 2026-06-28T17:48:39.571Z