Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective
The DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · cited 1×
“[25], and it can be applied to any types of machine learning models even under black-box settings.”
BackgroundPractical Secure Aggregation for Privacy-Preserving Machine Learning
Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3133982 · Cited by 3,956
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · cited 2×
“Some defense strategies have been presented to prevent the privacy leakage and can be categorized into three types: differential privacy [21, 24, 9, 17, 8], secure multi-party computation [4, 19, 3, 18], and data compression [28].”
BackgroundMethodSecureML: A System for Scalable Privacy-Preserving Machine Learning
Mohassel, P., & Zhang, Y. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.12 · Cited by 1,936 · cited 3×
“Some defense strategies have been presented to prevent the privacy leakage and can be categorized into three types: differential privacy [9, 10, 11, 12, 13], secure multi-party computation [14, 15, 16, 4], and data compression [6].”
BackgroundMethodZhu, L., & Han, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_2 · Cited by 1,906
Exploiting Unintended Feature Leakage in Collaborative Learning
Melis, L., Song, C., De Cristofaro, E., & Shmatikov, V. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00029 · Cited by 1,734
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Hitaj, B., Ateniese, G., & Perez-Cruz, F. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134012 · Cited by 1,377 · cited 2×
“Attribute inference attack [2, 6, 5, 11] tries to identify some sensitive attributes of training data.”
BackgroundFederated Learning for Mobile Keyboard Prediction
Hard, A., Rao, K., Mathews, R., Ramaswamy, S., Beaufays, F., Augenstein, S., Eichner, H., Kiddon, C., & Ramage, D. (2018) · arXiv · doi:10.48550/arxiv.1811.03604 · Cited by 1,148
Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
Wang, Z., Song, M., Zhang, Z., Song, Y., Wang, Q., & Qi, H. (2019) · IEEE INFOCOM 2019 - IEEE Conference on Computer Communications · doi:10.1109/infocom.2019.8737416 · Cited by 881
Learning Differentially Private Recurrent Language Models
McMahan, H. B., Ramage, D., Talwar, K., & Zhang, L. (2017) · arXiv · doi:10.48550/arxiv.1710.06963 · Cited by 849
Cited by
Rodríguez-Barroso, N., Jiménez-López, D., Luzón, M. V., Herrera, F., & Martínez-Cámara, E. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.09.011 · Cited by 296
Li, A., Sun, J., Zeng, X., Zhang, M., Li, H., & Chen, Y. (2021) · Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/3485730.3485929 · Cited by 139
Self-citationA Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy
Manzoor, H. U., Shabbir, A., Chen, A., Flynn, D., & Zoha, A. (2024) · Future Internet · doi:10.3390/fi16100374 · Cited by 58
Privacy-Enhancing Technologies in Federated Learning for the Internet of Healthcare Things: A Survey
Mosaiyebzadeh, F., Pouriyeh, S., Parizi, R. M., Sheng, Q. Z., Han, M., Zhao, L., Sannino, G., Ranieri, C. M., Ueyama, J., & Batista, D. M. (2023) · Electronics · doi:10.3390/electronics12122703 · Cited by 51
Privacy-Encoded Federated Learning Against Gradient-Based Data Reconstruction Attacks
Liu, H., Li, B., Gao, C., Xie, P., & Zhao, C. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3309095 · Cited by 27
Metadata
- Authors
- Sun, J., Li, A., Wang, B., Yang, H., Li, H., & Chen, Y.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 9307-9315
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3172312230
- Cited by
- 170
- References
- 11
- FWCI
- 14.19
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective. https://app.cochat.ai/papers/10.1109/cvpr46437.2021.00919
- The paper
- Sun, J., Li, A., Wang, B., Yang, H., Li, H., & Chen, Y. (2021). Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr46437.2021.00919
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.