GELU-Net: A Globally Encrypted, Locally Unencrypted Deep Neural Network for Privacy-Preserved Learning
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
Privacy is a fundamental challenge for a variety of smart applications that depend on data aggregation and collaborative learning across different entities. In this paper, we propose a novel privacy-preserved architecture where clients can collaboratively train a deep model while preserving the privacy of each client’s data. Our main strategy is to carefully partition a deep neural network to two non-colluding parties. One party performs linear computations on encrypted data utilizing a less complex homomorphic cryptosystem, while the other executes non-polynomial computations in plaintext but in a privacy-preserved manner. We analyze security and compare the communication and computation complexity with the existing approaches. Our extensive experiments on different datasets demonstrate not only stable training without accuracy loss, but also 14 to 35 times speedup compared to the state-of-the-art system.
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
A 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
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
Practical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
Applied cryptography: Protocols, algorithms, and source code in C
(1994) · Computer Law & Security Report · doi:10.1016/0267-3649(94)90017-5 · Cited by 3,411
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
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
Understanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
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 by
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
“In the latter case, some techniques ([8], [52], and [31]) might allow a cloud model to be trained by successive participants.”
BackgroundPrivacy-Preserving Deep Learning Based on Multiparty Secure Computation: A Survey
Zhang, Q., Xin, C., & Wu, H. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3058638 · Cited by 53
“As the dot product mainly involves addition and multiplication, HE can be directly applied such that the data matrix (or a data vector) is first encrypted by clients and then multiplied with the weight vector (or a weight matrix) by cloud servers [140], [142], [144], [150], [152]–[155].”
BackgroundSelf-citationNovikova, E., Fomichov, D., Kholod, I., & Filippov, E. (2022) · Sensors · doi:10.3390/s22082983 · Cited by 24
“Vertical Data encryption NN (DNN, RNN, CNN) SecureNN, or Iterative Affine, or Affine Additive HE [75,76] based on Paillier scheme”
MethodCryptoRec: Novel Collaborative Filtering Recommender Made Privacy-Preserving Easy
Wang, J., Jin, C., Tang, Q., Liu, Z., & Aung, K. M. M. (2022) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2021.3065752 · Cited by 9
Metadata
- Authors
- Zhang, Q., Wang, C., Wu, H., Xin, C., & Phuong, T. V.
- Venue
- Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
- Published
- 2018-07
- Pages
- 3933-3939
- OpenAlex
- W2808706611
- Cited by
- 79
- References
- 11
- FWCI
- 2.60
- Type
- conference paper
- Language
- en
- Open access
- bronze
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.