EUVIMEDEUVIMED entdecken
Crossref

Wasserstein Differential Privacy

Chengyi Yang, Jiayin Qi, Aimin Zhou

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (15) · 16299-16307

DOI: 10.1609/aaai.v38i15.29565 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Chengyi Yang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Differential privacy (DP) has achieved remarkable results in the field of privacy-preserving machine learning. However, existing DP frameworks do not satisfy all the conditions for becoming metrics, which prevents them from deriving better basic private properties and leads to exaggerated values on privacy budgets. We propose Wasserstein differential privacy (WDP), an alternative DP framework to measure the risk of privacy leakage, which satisfies the properties of symmetry and triangle inequality. We show and prove that WDP has 13 excellent properties, which can be theoretical supports for the better performance of WDP than other DP frameworks. In addition, we derive a general privacy accounting method called Wasserstein accountant, which enables WDP to be applied in stochastic gradient descent (SGD) scenarios containing subsampling. Experiments on basic mechanisms, compositions and deep learning show that the privacy budgets obtained by Wasserstein accountant are relatively stable and less influenced by order. Moreover, the overestimation on privacy budgets can be effectively alleviated. The code is available at https://github.com/Hifipsysta/WDP.

Zitieren

APA

Yang, C., Qi, J., & Zhou, A. (2024). Wasserstein Differential Privacy. Proceedings of the AAAI Conference on Artificial Intelligence, 38(15), 16299-16307. https://doi.org/10.1609/aaai.v38i15.29565

Vancouver

Yang C, Qi J, Zhou A. Wasserstein Differential Privacy. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(15):16299-16307. doi:10.1609/aaai.v38i15.29565

BibTeX
@article{Yang2024,
  author = {Yang, Chengyi and Qi, Jiayin and Zhou, Aimin},
  title = {Wasserstein Differential Privacy},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {15},
  pages = {16299--16307},
  doi = {10.1609/aaai.v38i15.29565}
}
Kostenlos starten →