PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining

Autor:	Kazmi, Mishaal, Lautraite, Hadrien, Akbari, Alireza, Tang, Qiaoyue, Soroco, Mauricio, Wang, Tao, Gambs, Sébastien, Lécuyer, Mathias
Rok vydání:	2024
Předmět:	Computer Science - Cryptography and Security Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We present PANORAMIA, a privacy leakage measurement framework for machine learning models that relies on membership inference attacks using generated data as non-members. By relying on generated non-member data, PANORAMIA eliminates the common dependency of privacy measurement tools on in-distribution non-member data. As a result, PANORAMIA does not modify the model, training data, or training process, and only requires access to a subset of the training data. We evaluate PANORAMIA on ML models for image and tabular data classification, as well as on large-scale language models. Comment: 36 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2402.09477 Zobrazit plný text záznamu View this record from Arxiv