PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915580048572416 |
|---|---|
| author | Melis, Luca Grange, Matthew Kalemaj, Iden Chadha, Karan Hu, Shengyuan Kashtelyan, Elena Bullock, Will |
| author_facet | Melis, Luca Grange, Matthew Kalemaj, Iden Chadha, Karan Hu, Shengyuan Kashtelyan, Elena Bullock, Will |
| contents | The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive tool for empirical differential privacy (DP) analysis, designed to evaluate privacy risks in ML models through state-of-the-art inference attacks and advanced privacy measurement techniques. To this end, PrivacyGuard implements a diverse suite of privacy attack -- including membership inference , extraction, and reconstruction attacks -- enabling both off-the-shelf and highly configurable privacy analyses. Its modular architecture allows for the seamless integration of new attacks, and privacy metrics, supporting rapid adaptation to emerging research advances. We make PrivacyGuard available at https://github.com/facebookresearch/PrivacyGuard. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23427 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning Melis, Luca Grange, Matthew Kalemaj, Iden Chadha, Karan Hu, Shengyuan Kashtelyan, Elena Bullock, Will Machine Learning The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive tool for empirical differential privacy (DP) analysis, designed to evaluate privacy risks in ML models through state-of-the-art inference attacks and advanced privacy measurement techniques. To this end, PrivacyGuard implements a diverse suite of privacy attack -- including membership inference , extraction, and reconstruction attacks -- enabling both off-the-shelf and highly configurable privacy analyses. Its modular architecture allows for the seamless integration of new attacks, and privacy metrics, supporting rapid adaptation to emerging research advances. We make PrivacyGuard available at https://github.com/facebookresearch/PrivacyGuard. |
| title | PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.23427 |