A General Framework for Data-Use Auditing of ML Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915121760043008 |
|---|---|
| author | Huang, Zonghao Gong, Neil Zhenqiang Reiter, Michael K. |
| author_facet | Huang, Zonghao Gong, Neil Zhenqiang Reiter, Michael K. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_15100 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A General Framework for Data-Use Auditing of ML Models Huang, Zonghao Gong, Neil Zhenqiang Reiter, Michael K. Cryptography and Security Machine Learning 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. |
| title | A General Framework for Data-Use Auditing of ML Models |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2407.15100 |