The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Privacy-Preserving Machine Learning With Fully Homomorphic Encryption for Deep Neural Network
Open accessAbstract
Fully homomorphic encryption (FHE) is a prospective tool for privacy-preserving machine learning (PPML). Several PPML models have been proposed based on various FHE schemes and approaches. Although FHE schemes are suitable as tools for implementing PPML models, previous PPML models based on FHE, such as CryptoNet, SEALion, and CryptoDL, are limited to simple and nonstandard types of machine learning models; they have not proven to be efficient and accurate with more practical and advanced datasets. Previous PPML schemes replaced non-arithmetic activation functions with simple arithmetic functions instead of adopting approximation methods and did not use bootstrapping, which enables continuous homomorphic evaluations. Thus, they could neither use standard activation functions nor employ large numbers of layers. In this work, we first implement the standard ResNet-20 model with the RNS-CKKS FHE with bootstrapping and verify the implemented model with the CIFAR-10 dataset and plaintext model parameters. Instead of replacing the non-arithmetic functions with simple arithmetic functions, we use state-of-the-art approximation methods to evaluate these non-arithmetic functions, such as ReLU and Softmax, with sufficient precision. Further, for the first time, we use the bootstrapping technique of the RNS-CKKS scheme in the proposed model, which enables us to evaluate an arbitrary deep learning model on encrypted data. We numerically verify that the proposed model with the CIFAR-10 dataset shows 98.43% identical results to the original ResNet-20 model with non-encrypted data. The classification accuracy of the proposed model is 92.43%±2.65%, which is quite close to that of the original ResNet-20 CNN model (91.89%). It takes approximately 3 h for inference on a dual Intel Xeon Platinum 8280 CPU (112 cores) with 172 GB of memory. We believe that this opens the possibility of applying FHE to an advanced deep PPML model.
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
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
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
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
(2016) · International Conference on Machine Learning · Cited by 1,270
Somewhat Practical Fully Homomorphic Encryption.
Fan, J., & Vercauteren, F. (2012) · Cited by 1,189
Bootstrapping for Approximate Homomorphic Encryption
Cheon, J. H., Han, K., Kim, A., Kim, M., & Song, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-78381-9_14 · Cited by 373
A Full RNS Variant of Approximate Homomorphic Encryption
Cheon, J. H., Han, K., Kim, A., Kim, M., & Song, Y. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-10970-7_16 · Cited by 357
CryptoDL: Deep Neural Networks over Encrypted Data
Hesamifard, E., Takabi, H., & Ghasemi, M. (2017) · arXiv · doi:10.48550/arxiv.1711.05189 · Cited by 306
Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted InferencePreprint
Chou, E., Beal, J., Levy, D., Yeung, S. Y., Haque, A., & Fei-Fei, L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.09953 · Cited by 277
Better Bootstrapping for Approximate Homomorphic Encryption
Han, K., & Ki, D. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-40186-3_16 · Cited by 193
Efficient Bootstrapping for Approximate Homomorphic Encryption with Non-sparse Keys
Bossuat, J.-P., Mouchet, C., Troncoso-Pastoriza, J., & Hubaux, J.-P. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-77870-5_21 · Cited by 176
Jung, W., Kim, S., Ahn, J. H., et al. (2021) · IACR Transactions on Cryptographic Hardware and Embedded Systems · doi:10.46586/tches.v2021.i4.114-148 · Cited by 173
Cheetah: Optimizing and Accelerating Homomorphic Encryption for Private Inference
Reagen, B., Choi, W.-S., Ko, Y., Lee, V. T., Lee, H.-H. S., Wei, G.-Y., & Brooks, D. M. (2021) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00013 · Cited by 170
Self-citationImproved Bootstrapping for Approximate Homomorphic Encryption
Chen, H., Chillotti, I., & Song, Y. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-17656-3_2 · Cited by 169
Al Badawi, A., Jin, C., Lin, J., Mun, C. F., Jie, S. J., Tan, B. H. M., Nan, X., Aung, K. M. M., & Chandrasekhar, V. R. (2021) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2020.3014636 · Cited by 167
nGraph-HE: a graph compiler for deep learning on homomorphically encrypted data
Boemer, F., Lao, Y., Cammarota, R., & Wierzynski, C. (2019) · Proceedings of the 16th ACM International Conference on Computing Frontiers · doi:10.1145/3310273.3323047 · Cited by 162
SHE: A Fast and Accurate Deep Neural Network for Encrypted DataPreprint
Lou, Q., & Jiang, L. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.00148 · Cited by 159
nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data
Boemer, F., Costache, A., Cammarota, R., & Wierzynski, C. (2019) · Proceedings of the 7th ACM Workshop on Encrypted Computing & Applied Homomorphic Cryptography · doi:10.1145/3338469.3358944 · Cited by 159
Lee, J.-W., Lee, E., Lee, Y., Kim, Y.-S., & No, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77870-5_22 · Cited by 142
Self-citationNumerical Method for Comparison on Homomorphically Encrypted Numbers
Cheon, J. H., Kim, D., Kim, D., Lee, H. H., & Lee, K. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-34621-8_15 · Cited by 141
Minimax Approximation of Sign Function by Composite Polynomial for Homomorphic Comparison
Lee, E., Lee, J.-W., No, J., & Kim, Y.-S. (2021) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2021.3105111 · Cited by 103
Self-citationPrecise Approximation of Convolutional Neural Networks for Homomorphically Encrypted Data
Lee, J., Lee, E., Lee, J.-W., Kim, Y., Kim, Y.-S., & No, J. (2023) · IEEE Access · doi:10.1109/access.2023.3287564 · Cited by 79
Self-citationHigh-Precision Bootstrapping for Approximate Homomorphic Encryption by Error Variance Minimization
Lee, Y., Lee, J.-W., Kim, Y.-S., Kim, Y., No, J., & Kang, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-06944-4_19 · Cited by 76
Self-citationApproximate Homomorphic Encryption with Reduced Approximation Error
Kim, A., Papadimitriou, A., & Polyakov, Y. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-95312-6_6 · Cited by 71
MP2ML: a mixed-protocol machine learning framework for private inference
Boemer, F., Cammarota, R., Demmler, D., Schneider, T. H., & Yalame, H. (2020) · International Conference on Availability, Reliability and Security (ARES) · doi:10.1145/3407023.3407045 · Cited by 69
Optimized homomorphic encryption solution for secure genome-wide association studies
Blatt, M., Gusev, A., Polyakov, Y., Rohloff, K. R., & Vaikuntanathan, V. (2020) · BMC Medical Genomics · doi:10.1186/s12920-020-0719-9 · Cited by 60
SEALion: a Framework for Neural Network Inference on Encrypted DataPreprint
van Elsloo, T., Patrini, G., & Ivey-Law, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.12840 · Cited by 57
A Hybrid of Dual and Meet-in-the-Middle Attack on Sparse and Ternary Secret LWE
Cheon, J. H., Hhan, M., Hong, S., & Son, Y. (2019) · IEEE Access · doi:10.1109/access.2019.2925425 · Cited by 52
Near-Optimal Polynomial for Modulus Reduction Using L2-Norm for Approximate Homomorphic Encryption
Lee, Y., Lee, J.-W., Kim, Y.-S., & No, J. (2020) · IEEE Access · doi:10.1109/access.2020.3014369 · Cited by 26
Self-citationnGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted DataPreprint
Boemer, F., Costache, A., Cammarota, R., & Wierzynski, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.04172 · Cited by 25
High-Precision and Low-Complexity Approximate Homomorphic Encryption by Error Variance MinimizationPreprint
Lee, Y., Lee, J., Kim, Y. S., Kang, H., & No, J. (2020) · IACR Cryptology ePrint Archive · Cited by 5
Self-citation
Cited by
Survey on Fully Homomorphic Encryption, Theory, and Applications
Marcolla, C., Sucasas, V., Manzano, M., Bassoli, R., Fitzek, F. H. P., & Aaraj, N. (2022) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3205665 · Cited by 323
Zhao, J., Bagchi, S., Avestimehr, S., Chan, K., Chaterji, S., Dimitriadis, D., Li, J., Li, N., Nourian, A., & Roth, H. (2025) · ACM Computing Surveys · doi:10.1145/3724113 · Cited by 63
FPT: A Fixed-Point Accelerator for Torus Fully Homomorphic Encryption
Van Beirendonck, M., D'Anvers, J.-P., Turan, F., & Verbauwhede, I. (2023) · Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3576915.3623159 · Cited by 38
Secure and Efficient Coded Multi-Access Edge Computing With Generalized Graph Neural Networks
Asheralieva, A., & Niyato, D. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3172117 · Cited by 15
Exploring Bitslicing Architectures for Enabling FHE-Assisted Machine Learning
Sinha, S., Saha, S., Alam, M., Agarwal, V., Chatterjee, A., Mishra, A., Khazanchi, D., & Mukhopadhyay, D. (2022) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2022.3204909 · Cited by 4
Metadata
- Authors
- Lee, J.-W., Kang, H., Lee, Y., Choi, W., Eom, J., Deryabin, M., Lee, E., Lee, J., Yoo, D., Kim, Y.-S., & No, J.-S.
- Venue
- IEEE Access
- Published
- 2022
- Volume
- 10
- Pages
- 30039-30054
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3173128495
- Cited by
- 414
- References
- 33
- FWCI
- 27.14
- Type
- journal article
- Language
- en
- Open access
- gold
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.