TY - GEN
T1 - Soteria
T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
AU - Sun, Jingwei
AU - Li, Ang
AU - Wang, Binghui
AU - Yang, Huanrui
AU - Li, Hai
AU - Chen, Yiran
N1 - Publisher Copyright: © 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Federated learning (FL) is a popular distributed learning framework that can reduce privacy risks by not explicitly sharing private data. However, recent works have demonstrated that sharing model updates makes FL vulnerable to inference attack. In this work, we show our key observation that the data representation leakage from gradients is the essential cause of privacy leakage in FL. We also provide an analysis of this observation to explain how the data presentation is leaked. Based on this observation, we propose a defense called Soteria against model inversion attack in FL. The key idea of our defense is learning to perturb data representation such that the quality of the reconstructed data is severely degraded, while FL performance is maintained. In addition, we derive a certified robustness guarantee to FL and a convergence guarantee to FedAvg, after applying our defense. To evaluate our defense, we conduct experiments on MNIST and CIFAR10 for defending against the DLG attack and GS attack. Without sacrificing accuracy, the results demonstrate that our proposed defense can increase the mean squared error between the reconstructed data and the raw data by as much as 160× for both DLG attack and GS attack, compared with baseline defense methods. Therefore, the privacy of the FL system is significantly improved. Our code can be found at https://github.com/jeremy313/Soteria.
AB - Federated learning (FL) is a popular distributed learning framework that can reduce privacy risks by not explicitly sharing private data. However, recent works have demonstrated that sharing model updates makes FL vulnerable to inference attack. In this work, we show our key observation that the data representation leakage from gradients is the essential cause of privacy leakage in FL. We also provide an analysis of this observation to explain how the data presentation is leaked. Based on this observation, we propose a defense called Soteria against model inversion attack in FL. The key idea of our defense is learning to perturb data representation such that the quality of the reconstructed data is severely degraded, while FL performance is maintained. In addition, we derive a certified robustness guarantee to FL and a convergence guarantee to FedAvg, after applying our defense. To evaluate our defense, we conduct experiments on MNIST and CIFAR10 for defending against the DLG attack and GS attack. Without sacrificing accuracy, the results demonstrate that our proposed defense can increase the mean squared error between the reconstructed data and the raw data by as much as 160× for both DLG attack and GS attack, compared with baseline defense methods. Therefore, the privacy of the FL system is significantly improved. Our code can be found at https://github.com/jeremy313/Soteria.
UR - https://www.scopus.com/pages/publications/85119568251
UR - https://www.scopus.com/pages/publications/85119568251#tab=citedBy
U2 - 10.1109/CVPR46437.2021.00919
DO - 10.1109/CVPR46437.2021.00919
M3 - Conference contribution
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 9307
EP - 9315
BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
PB - IEEE Computer Society
Y2 - 19 June 2021 through 25 June 2021
ER -