Privacy Leakage of Adversarial Training Models in Federated Learning Systems
Publication
, Conference
Zhang, J; Chen, Y; Li, H
Published in: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
January 1, 2022
Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks. In this work, we further reveal this unsettling property of AT by designing a novel privacy attack that is practically applicable to the privacy-sensitive Federated Learning (FL) systems. Using our method, the attacker can exploit AT models in the FL system to accurately reconstruct users' private training images even when the training batch size is large. Code is available at https://github.com/zjysteven/PrivayAttack_AT_FL.
Duke Scholars
Published In
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
DOI
EISSN
2160-7516
ISSN
2160-7508
Publication Date
January 1, 2022
Volume
2022-June
Start / End Page
107 / 113
Citation
APA
Chicago
ICMJE
MLA
NLM
Zhang, J., Chen, Y., & Li, H. (2022). Privacy Leakage of Adversarial Training Models in Federated Learning Systems. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (Vol. 2022-June, pp. 107–113). https://doi.org/10.1109/CVPRW56347.2022.00021
Zhang, J., Y. Chen, and H. Li. “Privacy Leakage of Adversarial Training Models in Federated Learning Systems.” In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2022-June:107–13, 2022. https://doi.org/10.1109/CVPRW56347.2022.00021.
Zhang J, Chen Y, Li H. Privacy Leakage of Adversarial Training Models in Federated Learning Systems. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2022. p. 107–13.
Zhang, J., et al. “Privacy Leakage of Adversarial Training Models in Federated Learning Systems.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2022-June, 2022, pp. 107–13. Scopus, doi:10.1109/CVPRW56347.2022.00021.
Zhang J, Chen Y, Li H. Privacy Leakage of Adversarial Training Models in Federated Learning Systems. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. 2022. p. 107–113.
Published In
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
DOI
EISSN
2160-7516
ISSN
2160-7508
Publication Date
January 1, 2022
Volume
2022-June
Start / End Page
107 / 113