Privacy-Preserving Deep Learning via Weight Transmission
Open accessThe DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Abstract
This paper considers the scenario that multiple data owners wish to apply a machine learning method over the combined dataset of all owners to obtain the best possible learning output but do not want to share the local datasets owing to privacy concerns. We design systems for the scenario that the stochastic gradient descent (SGD) algorithm is used as the machine learning method, because SGD (or its variants) is at the heart of recent deep learning techniques over neural networks. Our systems differ from the existing systems in the following features: 1) any activation function can be used, meaning that no privacy-preserving-friendly approximation is required; 2) gradients computed by SGD are not shared but the weight parameters are shared instead; and 3) robustness against colluding parties even in the extreme case that only one honest party exists. One of our systems requires a shared symmetric key among the data owners (trainers) to ensure the secrecy of the weight parameters against a central server. We prove that our systems, while privacy preserving, achieve the same learning accuracy as SGD and, hence, retain the merit of deep learning with respect to accuracy. Finally, we conduct several experiments using benchmark datasets and show that our systems outperform the previous system in terms of learning accuracies.
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
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
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
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665 · cited 1×
“Each trainer in our system re-uses the Keras official example codes [42] (of CNN) and [43] (of ResNetv1 [44] and ResNetv2 [45]) for training and testing over the CIFAR-10 and CIFAR-100 datasets.”
MethodMembership 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 5×
“regularization as suggested in [35] or dropouts as in Hedge 2.”
BackgroundInfluentialPractical 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 12×
“In addition, a comparison with the systems in [2], [4] is given in Table I.”
BackgroundMethodResultInfluentialSecureML: 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×
“There were no experimental results on CNNs reported in [19] perhaps owing to the hurdles of implementing the Fast Fourier Transform in the case of secure computation.”
MethodInfluentialPrivacy-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
Self-citation
Cited by
Yin, X., Zhu, Y., & Hu, J. (2022) · ACM Computing Surveys · doi:10.1145/3460427 · Cited by 638
Yang, Q., Liu, Y., Cheng, Y., Kang, Y., Chen, T., & Yu, H. (2019) · Synthesis lectures on artificial intelligence and machine learning · doi:10.2200/s00960ed2v01y201910aim043 · Cited by 261
Abnormal client behavior detection in federated learning
Li, S., Cheng, Y., Liu, Y., Wang, W., & Chen, T. (2019) · arXiv · doi:10.48550/arxiv.1910.09933 · Cited by 122
“In such a federated setting, the federated averaging ( FedAvg ) algorithm is widely-used for federated model training, which takes either the model average or the gradient average of the local model weight or gradient updates from the clients [2, 7–10].”
MethodPixel-Based Image Encryption Without Key Management for Privacy-Preserving Deep Neural Networks
Sirichotedumrong, W., Kinoshita, Y., & Kiya, H. (2019) · IEEE Access · doi:10.1109/access.2019.2959017 · Cited by 105
Survey: Leakage and Privacy at Inference Time
Jegorova, M., Kaul, C., Mayor, C., O'Neil, A. Q., Weir, A., Murray-Smith, R., & Tsaftaris, S. A. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3229593 · Cited by 77
Metadata
- Authors
- Phong, L. T., & Phuong, T. T.
- Venue
- IEEE Transactions on Information Forensics and Security
- Published
- 2019-11
- Volume
- 14
- Issue
- 11
- Pages
- 3003-3015
- ISSN
- 1556-6013 (ISSN-L)
- 1556-6021
- OpenAlex
- W2913608349
- Cited by
- 114
- References
- 16
- FWCI
- 7.25
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Privacy-Preserving Deep Learning via Weight Transmission. https://app.cochat.ai/papers/10.1109/tifs.2019.2911169
- The paper
- Phong, L. T., & Phuong, T. T. (2019). Privacy-Preserving Deep Learning via Weight Transmission. IEEE Transactions on Information Forensics and Security. https://doi.org/10.1109/tifs.2019.2911169
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.