Secure Outsourced Matrix Computation and Application to Neural Networks
Open accessThe DOI matches its Crossref record; 37 of the 37 references it cites were found in a registry or an index.
Abstract
Homomorphic Encryption (HE) is a powerful cryptographic primitive to address privacy and security issues in outsourcing computation on sensitive data to an untrusted computation environment. Comparing to secure Multi-Party Computation (MPC), HE has advantages in supporting non-interactive operations and saving on communication costs. However, it has not come up with an optimal solution for modern learning frameworks, partially due to a lack of efficient matrix computation mechanisms. In this work, we present a practical solution to encrypt a matrix homomorphically and perform arithmetic operations on encrypted matrices. Our solution includes a novel matrix encoding method and an efficient evaluation strategy for basic matrix operations such as addition, multiplication, and transposition. We also explain how to encrypt more than one matrix in a single ciphertext, yielding better amortized performance. Our solution is generic in the sense that it can be applied to most of the existing HE schemes. It also achieves reasonable performance for practical use; for example, our implementation takes 9.21 seconds to multiply two encrypted square matrices of order 64 and 2.56 seconds to transpose a square matrix of order 64. Our secure matrix computation mechanism has a wide applicability to our new framework E2DM, which stands for encrypted data and encrypted model. To the best of our knowledge, this is the first work that supports secure evaluation of the prediction phase based on both encrypted data and encrypted model, whereas previous work only supported applying a plain model to encrypted data. As a benchmark, we report an experimental result to classify handwritten images using convolutional neural networks (CNN). Our implementation on the MNIST dataset takes 28.59 seconds to compute ten likelihoods of 64 input images simultaneously, yielding an amortized rate of 0.45 seconds per image.
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
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
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408
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×
“After Gentry’s first construction of a fully HE scheme [22], there have been several attempts to improve efficiency and flexibility of HE systems.”
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322
Deep learning for healthcare: review, opportunities and challenges
Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018) · Briefings in Bioinformatics · doi:10.1093/bib/bbx044 · Cited by 3,076 · cited 1×
“Recently deep neural network based models have been demonstrated to achieve great success in a number of health care applications [36], and a natural question is whether we can outsource such learned models to a third party and evaluate new samples in a secure manner? There are several different scenarios depending on…”
Self-citationSomewhat Practical Fully Homomorphic Encryption.Preprint
Fan, J., & Vercauteren, F. (2012) · IACR Cryptology ePrint Archive · Cited by 2,597
Homomorphic Encryption for Arithmetic of Approximate Numbers
Cheon, J. H., Kim, A., Kim, M., & Song, Y. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-70694-8_15 · Cited by 2,522 · cited 7×
“In the current literature, most of practical HE schemes [8, 9, 14, 19] support their own packing methods to achieve better amortized complexity of homomorphic operations.”
InfluentialSelf-citationSecureML: 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×
“Mohassel and Zhang [39] applied the mixed-protocol framework of [17] to implement neural networks training and evaluation in a two-party computation setting.”
(Leveled) fully homomorphic encryption without bootstrapping
Brakerski, Z., Gentry, C., & Vaikuntanathan, V. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090262 · Cited by 1,782
Cited by
Privacy-Preserving Byzantine-Robust Federated Learning via Blockchain Systems
Miao, Y., Liu, Z., Li, H., Choo, K.-K. R., & Deng, R. H. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3196274 · Cited by 303
Chen, H., Dai, W., Kim, M., & Song, Y. (2019) · Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3319535.3363207 · Cited by 256
Self-citationCHET: an optimizing compiler for fully-homomorphic neural-network inferencing
Dathathri, R., Saarikivi, O., Chen, H., Laine, K., Lauter, K., Maleki, S., Musuvathi, M., & Mytkowicz, T. (2019) · Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation · doi:10.1145/3314221.3314628 · Cited by 235
“Many have observed the need and suitability of FHE for machine learning tasks [11, 23, 25, 28].”
BackgroundSelf-citationHomomorphic Encryption for Machine Learning in Medicine and Bioinformatics
Wood, A., Najarian, K., & Kahrobaei, D. (2021) · ACM Computing Surveys · doi:10.1145/3394658 · Cited by 179
TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption
Benaissa, A., Retiat, B., Cebere, B., & Belfedhal, A. E. (2021) · arXiv · doi:10.48550/arxiv.2104.03152 · Cited by 111
Privacy-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
“Meanwhile, by considering the computation complexity of each type of operation, e.g., HE addition is faster than HE multiplication and plaintext computation is cheaper than ciphertext counterpart, the total cost can be optimized by securely selecting the cheaper operations [50], [76], [141], [146].”
BackgroundMethodInfluentialHEAX: An Architecture for Computing on Encrypted Data
Riazi, M. S., Laine, K., Pelton, B., & Dai, W. (2019) · arXiv · doi:10.48550/arxiv.1909.09731 · Cited by 26
A comprehensive survey and taxonomy on privacy-preserving deep learning
Tran, A.-T., Luong, T.-D., & Huynh, V.-N. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127345 · Cited by 21
COLLAGENE enables privacy-aware federated and collaborative genomic data analysis
Li, W., Kim, M., Zhang, K., Chen, H., Jiang, X., & Harmanci, A. (2023) · Genome Biology · doi:10.1186/s13059-023-03039-z · Cited by 16
“For matrix multiplications, we adopt a simplification of the approach devised in Jiang et al. [114]: Given two plaintext matrices of sizes ( a × b ) and ( b × c ) , we first generate the column expansion of the M 1 and row expansion of M 2 , which are basically repetitions of columns and rows of…”
BackgroundMethodSelf-citation
Metadata
- Authors
- Jiang, X., Kim, M., Lauter, K., & Song, Y.
- Venue
- Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2018-10-15
- Volume
- 2018
- Pages
- 1209-1222
- OpenAlex
- W2889746123
- Cited by
- 313
- References
- 37
- FWCI
- 10.92
- Type
- conference paper
- 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.