Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile-Reference-Cited by-同舟云学术

Probing the Transition to Dataset-Level Privacy in ML Models Using an Output-Specific and Data-Resolved Privacy Profile

Published:2023-11-26 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security
language:
Short-container-title:

Author:

LeBlond Tyler¹^ORCID,Munoz Joseph¹^ORCID,Lu Fred¹^ORCID,Fuchs Maya¹^ORCID,Zaresky-Williams Elliot¹^ORCID,Raff Edward²^ORCID,Testa Brian³^ORCID

Affiliation:

1. Booz Allen Hamilton, Annapolis Junction, MD, USA

2. Booz Allen Hamilton, Jamesville, NY, USA

3. Air Force Research Laboratory, Rome, NY, USA

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3605764.3623904

Reference35 articles.

1. Deep Learning with Differential Privacy

2. Differential privacy has disparate impact on model accuracy;Bagdasaryan Eugene;Advances in Neural Information Processing Systems,2019

3. DP-Sniper: Black-Box Discovery of Differential Privacy Violations using Classifiers

4. Lucas Bourtoule , Varun Chandrasekaran , Christopher A Choquette-choo, Hengrui Jia , Adelin Travers , Baiwu Zhang , David Lie , and Nicolas Papernot . 2021 . Machine Unlearning. In IEEE Symposium of Security and Privacy. Lucas Bourtoule, Varun Chandrasekaran, Christopher A Choquette-choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot. 2021. Machine Unlearning. In IEEE Symposium of Security and Privacy.

5. Jonathan Brophy and Daniel Lowd . 2021 . Machine Unlearning for Random Forests . In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research , Vol. 139), , Marina Meila and Tong Zhang (Eds.). PMLR, 1092-- 1104 . https://proceedings.mlr.press/v139/brophy21a.html Jonathan Brophy and Daniel Lowd. 2021. Machine Unlearning for Random Forests. In Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 139), , Marina Meila and Tong Zhang (Eds.). PMLR, 1092--1104. https://proceedings.mlr.press/v139/brophy21a.html

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. SoK: A Review of Differentially Private Linear Models For High-Dimensional Data;2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML);2024-04-09