GRNN: Generative Regression Neural Network—A Data Leakage Attack for Federated Learning
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Data privacy has become an increasingly important issue in Machine Learning (ML) , where many approaches have been developed to tackle this challenge, e.g., cryptography ( Homomorphic Encryption (HE) , Differential Privacy (DP) ) and collaborative training (Secure Multi-Party Computation (MPC) , Distributed Learning, and Federated Learning (FL) ). These techniques have a particular focus on data encryption or secure local computation. They transfer the intermediate information to the third party to compute the final result. Gradient exchanging is commonly considered to be a secure way of training a robust model collaboratively in Deep Learning (DL) . However, recent researches have demonstrated that sensitive information can be recovered from the shared gradient. Generative Adversarial Network (GAN) , in particular, has shown to be effective in recovering such information. However, GAN based techniques require additional information, such as class labels that are generally unavailable for privacy-preserved learning. In this article, we show that, in the FL system, image-based privacy data can be easily recovered in full from the shared gradient only via our proposed Generative Regression Neural Network (GRNN) . We formulate the attack to be a regression problem and optimize two branches of the generative model by minimizing the distance between gradients. We evaluate our method on several image classification tasks. The results illustrate that our proposed GRNN outperforms state-of-the-art methods with better stability, stronger robustness, and higher accuracy. It also has no convergence requirement to the global FL model. Moreover, we demonstrate information leakage using face re-identification. Some defense strategies are also discussed in this work.
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
A training algorithm for optimal margin classifiers
Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992) · Proceedings of the fifth annual workshop on Computational learning theory · doi:10.1145/130385.130401 · Cited by 11,992
Improved training of Wasserstein GANs
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017) · arXiv · doi:10.48550/arxiv.1704.00028 · Cited by 6,800 · cited 1×
“We followed the design principle of iWGAN [15] where the image is generated from a coarse scale to a ine-scale gradually.”
MethodDeep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
Parkhi, O. M., Vedaldi, A., & Zisserman, A. (2015) · Procedings of the British Machine Vision Conference 2015 · doi:10.5244/c.29.41 · Cited by 5,479
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks
Moosavi-Dezfooli, S.-M., Fawzi, A., & Frossard, P. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.282 · Cited by 5,317
Image Quality Metrics: PSNR vs. SSIM
Hore, A., & Ziou, D. (2010) · 2010 20th International Conference on Pattern Recognition · doi:10.1109/icpr.2010.579 · Cited by 4,943
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×
“However, recent studies found that the gradient-sharing scheme is in fact not privacypreserved [11, 21, 33, 43].”
BackgroundThe Limitations of Deep Learning in Adversarial Settings
Papernot, N., McDaniel, P., Jha, S., Fredrikson, M., Celik, Z. B., & Swami, A. (2016) · 2016 IEEE European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp.2016.36 · Cited by 3,993
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Fredrikson, M., Jha, S., & Ristenpart, T. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813677 · Cited by 2,961
Statistical Inference for Probabilistic Functions of Finite State Markov Chains
Baum, L. E., & Petrie, T. (1966) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177699147 · Cited by 2,775
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×
“, Federated Stochastic Gradient Descent (FedSGD) [58], Federated Averaging (FedAvg) [42]) proposed to aggregate gradients that are calculated based on local models at client nodes.”
BackgroundSecureML: 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 1×
“Cryptography based privacy-preserving methods, such as secure aggregation protocol [5], Homomorphic Encryption (HE) [3, 27], Diferential Privacy (DP) [7, 9, 10] have been developed for privacy-preserving learning, for instance, linear regression model [12, 35], decision trees [4, 6], deep neural networks [19, 20, 27].”
MethodZhu, 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 · cited 3×
“However, recent studies found that the gradient-sharing scheme is in fact not privacypreserved [11, 21, 33, 43].”
BackgroundMethodPrivacy-Preserving Deep Learning via Additively Homomorphic Encryption
Phong, L. T., Aono, Y., Hayashi, T., Wang, L., & Moriai, S. (2018) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2787987 · Cited by 1,662 · cited 1×
“Gradient encryption is an alternative defense strategy [1, 16, 17], where HE is used to encrypt the gradient shared between server and clients, therefore, the aggregation can be done directly on the encrypted gradient.”
MethodDeep 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 3×
“However, recent studies found that the gradient-sharing scheme is in fact not privacypreserved [11, 21, 33, 43].”
BackgroundMethodDeep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Lin, Y., Han, S., Mao, H., Wang, Y., & Dally, W. J. (2017) · arXiv · doi:10.48550/arxiv.1712.01887 · Cited by 1,134
Differentially Private Federated Learning: A Client Level Perspective
Geyer, R. C., Klein, T., & Nabi, M. (2017) · arXiv · doi:10.48550/arxiv.1712.07557 · Cited by 1,052
Hardy, S., Henecka, W., Ivey-Law, H., Nock, R., Patrini, G., Smith, G., & Thorne, B. (2017) · arXiv · doi:10.48550/arxiv.1711.10677 · Cited by 431 · cited 1×
“Gradient encryption is an alternative defense strategy [1, 16, 17], where HE is used to encrypt the gradient shared between server and clients, therefore, the aggregation can be done directly on the encrypted gradient.”
MethodCryptoDL: Deep Neural Networks over Encrypted Data
Hesamifard, E., Takabi, H., & Ghasemi, M. (2017) · arXiv · doi:10.48550/arxiv.1711.05189 · Cited by 306 · cited 1×
“Cryptography based privacy-preserving methods, such as secure aggregation protocol [5], Homomorphic Encryption (HE) [3, 27], Diferential Privacy (DP) [7, 9, 10] have been developed for privacy-preserving learning, for instance, linear regression model [12, 35], decision trees [4, 6], deep neural networks [19, 20, 27].”
Method
Cited by
Differential Privacy for Deep and Federated Learning: A Survey
Ouadrhiri, A. E., & Abdelhadi, A. (2022) · IEEE Access · doi:10.1109/access.2022.3151670 · Cited by 445
“Attackers may query the trained learning model to recover the original training dataset [9]– this type of attack is called model inversion attacks.”
BackgroundMethodInfluentialFan, Z., Yan, Z., & Wen, S. (2023) · Sustainability · doi:10.3390/su151813493 · Cited by 346
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
“[65], whose comparison with others than Zhu and Han [12] remains undone.”
MethodResultThe Impact of Adversarial Attacks on Federated Learning: A Survey
Kumar, K. N., Mohan, C. K., & Cenkeramaddi, L. R. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3322785 · Cited by 180
“Privacy-centricthreats[14],[15],[16]relatetoparticipant data exposure, risking the leakage of sensitive information and eroding trust in the FL system.”
BackgroundPreserving data privacy in machine learning systems
El Mestari, S. Z., Lenzini, G., & Demirci, H. (2024) · Computers & Security · doi:10.1016/j.cose.2023.103605 · Cited by 162
“Another approach to address the problems is in the work of Zhu et al. (2019) was introduced by Ren et al. (2022) where a Generative Ad-versarial Neural Network (GAN) was used as an attack model, their approach was more stable and scales well on large-resolution images.”
Method
Metadata
- Authors
- Ren, H., Deng, J., & Xie, X.
- Venue
- ACM Transactions on Intelligent Systems and Technology
- Published
- 2022-05-03
- Volume
- 13
- Issue
- 4
- Pages
- 1-24
- ISSN
- 2157-6904 (ISSN-L)
- 2157-6912
- OpenAlex
- W3158675315
- Cited by
- 112
- References
- 26
- FWCI
- 8.40
- Type
- journal article
- Language
- en
- Open access
- green
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
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.