Private, Yet Practical, Multiparty Deep Learning
The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
In this paper, we consider the problem of multiparty deep learning (MDL), wherein autonomous data owners jointly train accurate deep neural network models without sharing their private data. We design, implement, and evaluate ∝MDL, a new MDL paradigm built upon three primitives: asynchronous optimization, lightweight homomorphic encryption, and threshold secret sharing. Compared with prior work, ∝MDL departs in significant ways: a) besides providing explicit privacy guarantee, it retains desirable model utility, which is paramount for accuracy-critical domains; b) it provides an intuitive handle for the operator to gracefully balance model utility and training efficiency; c) moreover, it supports delicate control over communication and computational costs by offering two variants, operating under loose and tight coordination respectively, thus optimizable for given system settings (e.g., limited versus sufficient network bandwidth). Through extensive empirical evaluation using benchmark datasets and deep learning architectures, we demonstrate the efficacy of ∝MDL.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612 · cited 1×
“The recent advances in deep learning ( DL ) [1] have led to breakthroughs in long-standing artificial intelligence tasks (e.g., image recognition, language translation, and even playing Go [2]), enabling use cases previously considered strictly experimental.”
BackgroundShamir, A. (1979) · Communications of the ACM · doi:10.1145/359168.359176 · Cited by 13,756 · cited 1×
“We use the Shamir’s secret sharing protocol [13] as a concrete instance.”
MethodA public key cryptosystem and a signature scheme based on discrete logarithms
Elgamal, T. (1985) · IEEE Transactions on Information Theory · doi:10.1109/tit.1985.1057074 · Cited by 8,059
Public-Key Cryptosystems Based on Composite Degree Residuosity Classes
Paillier, P. (2007) · Lecture Notes in Computer Science · doi:10.1007/3-540-48910-x_16 · Cited by 7,250
Fully homomorphic encryption using ideal lattices
Gentry, C. (2009) · Proceedings of the forty-first annual ACM symposium on Theory of computing · doi:10.1145/1536414.1536440 · Cited by 6,806 · cited 1×
“Unlike fully homomorphic encryption [15] that supports homomorphism for arbitrary functions, the cryptosystem above only supports multiplicative homomorphism via modular ex-ponentiation, thereby being practically efficient.”
BackgroundDeep 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
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
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 6×
“…straightforward solution is to perform differentially private randomization [6] to the local gradients, with the hope that releasing such local gradients does not overly leak the private information of the local data [18], [5], which we refer to as the local differential privacy ( LDP ) solution.”
BackgroundMethodInfluential
Cited by
Verifynet: Secure and verifiable federated learning
Xu, G., Li, H., Liu, S., Yang, K., & Lin, X. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2929409 · Cited by 839
Efficient and Privacy-Enhanced Federated Learning for Industrial Artificial Intelligence
Hao, M., Li, H., Luo, X., Xu, G., Yang, H., & Liu, S. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2945367 · Cited by 569
“Available: https://github.com/homenc/HElib PPM [21].”
MethodPrivacy preservation in federated learning: An insightful survey from the GDPR perspective
Truong, N., Sun, K., Wang, S., Guitton, F., & Guo, Y. (2021) · Computers & Security · doi:10.1016/j.cose.2021.102402 · Cited by 399
A review of privacy-preserving techniques for deep learning
Boulemtafes, A., Derhab, A., & Challal, Y. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.11.041 · Cited by 211
“(2017) [28] Train accurate deep neural network models jointly by participants Encryption - Lightweight HE – El Gamal - Threshold secret sharing - Shamir’s SS [ρ(rho)-ρ(rho)-rho)visibility] - Local differential privacy (DP) - DP randomization, sampled from symmetric distributions e.”
BackgroundMethodInfluentialPrivacy-Preserving Federated Learning for Internet of Medical Things Under Edge Computing
Wang, R., Lai, J., Zhang, Z., Li, X., Vijayakumar, P., & Karuppiah, M. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3157725 · Cited by 203
“In order to make fair comparisons, MNIST, CIFAR10 data sets are used to run another three federated learning algorithms, which are differential privacy federated Learning [30], homomorphic encrypted federated Learning [31], and FedAvg (Primitive federated Learning) [32].”
MethodChallenges, Applications and Design Aspects of Federated Learning: A Survey
Rahman, K. M. J., Ahmed, F., Akhter, N., Hasan, M., Amin, R., Aziz, K. E., Islam, A. K. M. M., Mukta, M. S. H., & Islam, A. K. M. N. (2021) · IEEE Access · doi:10.1109/access.2021.3111118 · Cited by 147
A Survey on Differentially Private Machine Learning [Review Article]
Gong, M., Xie, Y., Pan, K., Feng, K., & Qin, A. K. (2020) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2020.2976185 · Cited by 115
A Review of Privacy-Preserving Federated Learning for the Internet-of-Things
Briggs, C., Fan, Z., & Andras, P. (2021) · Studies in Computational Intelligence · doi:10.1007/978-3-030-70604-3_2 · Cited by 101
“[105] 2017 Method for encrypting user updates during distributed training, decryptable only when many clients have participated in the distributed learning objective HE, SMC Gradient updates are encrypted using homomorphic encryption.”
MethodBlockchain-Federated-Learning and Deep Learning Models for COVID-19 Detection Using CT Imaging
Kumar, R., Khan, A. A., Kumar, J., Zakria, Golilarz, N. A., Zhang, S., Ting, Y., Zheng, C., & Wang, W. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3076767 · Cited by 57
Antwi-Boasiako, E., Zhou, S., Liao, Y., Liu, Q., Wang, Y., & Owusu-Agyemang, K. (2021) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2021.102949 · Cited by 31
Metadata
- Authors
- Zhang, X., Ji, S., Wang, H., & Wang, T.
- Venue
- 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)
- Publisher
- IEEE
- Published
- 2017-06
- Pages
- 1442-1452
- OpenAlex
- W2736194861
- Cited by
- 74
- References
- 12
- FWCI
- 1.91
- 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
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.