PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912087277568000 |
|---|---|
| author | Kazmi, Mishaal Lautraite, Hadrien Akbari, Alireza Tang, Qiaoyue Soroco, Mauricio Wang, Tao Gambs, Sébastien Lécuyer, Mathias |
| author_facet | Kazmi, Mishaal Lautraite, Hadrien Akbari, Alireza Tang, Qiaoyue Soroco, Mauricio Wang, Tao Gambs, Sébastien Lécuyer, Mathias |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09477 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining Kazmi, Mishaal Lautraite, Hadrien Akbari, Alireza Tang, Qiaoyue Soroco, Mauricio Wang, Tao Gambs, Sébastien Lécuyer, Mathias Cryptography and Security Machine Learning 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. |
| title | PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2402.09477 |