A General Framework for Data-Use Auditing of ML Models

July 21, 2024 ยท Declared Dead ยท ๐Ÿ› Conference on Computer and Communications Security

๐Ÿ‘ป CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Zonghao Huang, Neil Zhenqiang Gong, Michael K. Reiter arXiv ID 2407.15100 Category cs.CR: Cryptography & Security Cross-listed cs.LG Citations 18 Venue Conference on Computer and Communications Security Last Checked 3 months ago
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Cryptography & Security

Died the same way โ€” ๐Ÿ‘ป Ghosted