The DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
SecureNN: 3-Party Secure Computation for Neural Network Training
Open accessAbstract
Neural Networks (NN) provide a powerful method for machine learning training and inference. To effectively train, it is desirable for multiple parties to combine their data – however, doing so conflicts with data privacy. In this work, we provide novel three-party secure computation protocols for various NN building blocks such as matrix multiplication, convolutions, Rectified Linear Units, Maxpool, normalization and so on. This enables us to construct three-party secure protocols for training and inference of several NN architectures such that no single party learns any information about the data. Experimentally, we implement our system over Amazon EC2 servers in different settings. Our work advances the state-of-the-art of secure computation for neural networks in three ways: 1. Scalability: We are the first work to provide neural network training on Convolutional Neural Networks (CNNs) that have an accuracy of > 99% on the MNIST dataset; 2. Performance: For secure inference, our system outperforms prior 2 and 3-server works (SecureML, MiniONN, Chameleon, Gazelle) by 6×-113× (with larger gains obtained in more complex networks). Our total execution times are 2 − 4× faster than even just the online times of these works. For secure training, compared to the only prior work (SecureML) that considered a much smaller fully connected network, our protocols are 79× and 7× faster than their 2 and 3-server protocols. In the WAN setting, these improvements are more dramatic and we obtain an improvement of 553×! 3. Security: Our protocols provide two kinds of security: full security (privacy and correctness) against one semi-honest corruption and the notion of privacy against one malicious corruption [Araki et al. CCS’16]. All prior works only provide semi-honest security and ours is the first system to provide any security against malicious adversaries for the secure computation of complex algorithms such as neural network inference and training. Our gains come from a significant improvement in communication through the elimination of expensive garbled circuits and oblivious transfer protocols.
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
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
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Goldreich, O., Micali, S., & Wigderson, A. (1987) · Proceedings of the nineteenth annual ACM conference on Theory of computing - STOC '87 · doi:10.1145/28395.28420 · Cited by 3,590
Universally composable security: a new paradigm for cryptographic protocols
Canetti, R. (2001) · Proceedings 42nd IEEE Symposium on Foundations of Computer Science · doi:10.1109/sfcs.2001.959888 · Cited by 3,309
Completeness theorems for non-cryptographic fault-tolerant distributed computation
Ben-Or, M., & Wigderson, A. (1988) · Proceedings of the twentieth annual ACM symposium on Theory of computing - STOC '88 · doi:10.1145/62212.62213 · Cited by 2,524
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
SecureML: 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 10×
“However, general purpose MPC/3PC work over low-level circuits (either arithmetic or boolean) and for complex tasks such as neural network training, this leads to highly inefficient protocols that can take “forever to execute” (also pointed out by [21, 26, 33, 36]).”
BackgroundMethodResultInfluentialMultiparty unconditionally secure protocols
Chaum, D., Crépeau, C., & Damgard, I. (1988) · Proceedings of the twentieth annual ACM symposium on Theory of computing - STOC '88 · doi:10.1145/62212.62214 · Cited by 1,544
Security and Composition of Multiparty Cryptographic Protocols
Canetti, R. (2000) · Journal of Cryptology · doi:10.1007/s001459910006 · Cited by 1,403
(2016) · International Conference on Machine Learning · Cited by 1,270
Privacy Preserving Data Mining
Lindell, Y., & Pinkas, B. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-44598-6_3 · Cited by 1,077
Efficient Multiparty Protocols Using Circuit Randomization
Beaver, D. (2007) · Lecture Notes in Computer Science · doi:10.1007/3-540-46766-1_34 · Cited by 893
ABY - A Framework for Efficient Mixed-Protocol Secure Two-Party Computation
Demmler, D., Schneider, T., & Zohner, M. (2015) · Proceedings 2015 Network and Distributed System Security Symposium · doi:10.14722/ndss.2015.23113 · Cited by 827
Oblivious Neural Network Predictions via MiniONN Transformations
Liu, J., Juuti, M., Lu, Y., & Asokan, N. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134056 · Cited by 691
Sharemind: A Framework for Fast Privacy-Preserving Computations
Bogdanov, D., Laur, S., & Willemson, J. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88313-5_13 · Cited by 690
Machine Learning Classification over Encrypted Data
Bost, R., Popa, R. A., Tu, S., & Goldwasser, S. (2015) · Proceedings 2015 Network and Distributed System Security Symposium · doi:10.14722/ndss.2015.23241 · Cited by 674
Ben-Or, M., Goldwasser, S., & Wigderson, A. (1988) · Cited by 495
ABY 3: A Mixed Protocol Framework for Machine Learning
Mohassel, P., & Rindal, P. (2018) · Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3243734.3243760 · Cited by 432
Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications
Riazi, M. S., Weinert, C., Tkachenko, O., Songhori, E. M., Schneider, T., & Koushanfar, F. (2018) · Proceedings of the 2018 on Asia Conference on Computer and Communications Security · doi:10.1145/3196494.3196522 · Cited by 410
High-Throughput Semi-Honest Secure Three-Party Computation with an Honest Majority
Araki, T., Furukawa, J., Lindell, Y., Nof, A., & Ohara, K. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978331 · Cited by 405
Shoaf, H. R. (2003) · Plastic Surgical Nursing · doi:10.1097/00006527-200323020-00009 · Cited by 283
Privacy-preserving matrix factorization
Nikolaenko, V., Ioannidis, S., Weinsberg, U., Joye, M., Taft, N., & Boneh, D. (2013) · Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security - CCS '13 · doi:10.1145/2508859.2516751 · Cited by 271
Privacy-Preserving Classification on Deep Neural Network.Preprint
Chabanne, H., de Wargny, A., Milgram, J., Morel, C., & Prouff, E. (2017) · IACR Cryptology ePrint Archive · Cited by 224
Multiparty Computation for Interval, Equality, and Comparison Without Bit-Decomposition Protocol
Nishide, T., & Ohta, K. (2007) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-71677-8_23 · Cited by 221
Homomorphic encryption and secure comparison
Damgard, I., Geisler, M., & Kroigard, M. (2008) · International Journal of Applied Cryptography · doi:10.1504/ijact.2008.017048 · Cited by 221
High-performance secure multi-party computation for data mining applications
Bogdanov, D., Niitsoo, M., Toft, T., & Willemson, J. (2012) · International Journal of Information Security · doi:10.1007/s10207-012-0177-2 · Cited by 212
Privately Evaluating Decision Trees and Random Forests
Wu, D. J., Feng, T., Naehrig, M., & Lauter, K. (2016) · Proceedings on Privacy Enhancing Technologies · doi:10.1515/popets-2016-0043 · Cited by 183
Improved Primitives for Secure Multiparty Integer Computation
Catrina, O., & de Hoogh, S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15317-4_13 · Cited by 178
Gazelle: A Low Latency Framework for Secure Neural Network Inference
Juvekar, C., Vaikuntanathan, V., & Chandrakasan, A. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1801.05507 · Cited by 164
High-Throughput Secure Three-Party Computation for Malicious Adversaries and an Honest Majority
Furukawa, J., Lindell, Y., Nof, A., & Weinstein, O. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-56614-6_8 · Cited by 153
A Zero-One Law for Boolean Privacy
Chor, B., & Kushilevitz, E. (1991) · SIAM Journal on Discrete Mathematics · doi:10.1137/0404004 · Cited by 147
Fast Large-Scale Honest-Majority MPC for Malicious Adversaries
Chida, K., Genkin, D., Hamada, K., Ikarashi, D., Kikuchi, R., Lindell, Y., & Nof, A. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-96878-0_2 · Cited by 144
Fast and Secure Three-party Computation: The Garbled Circuit Approach
Mohassel, P., Rosulek, M., & Zhang, Y. (2015) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/2810103.2813705 · Cited by 112
Lindell, Y., & Nof, A. (2017) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3133956.3133999 · Cited by 96
Cited by
End-to-end privacy preserving deep learning on multi-institutional medical imaging
Kaissis, G., Ziller, A., Passerat-Palmbach, J., Ryffel, T., Usynin, D., Trask, A., Lima, I., Mancuso, J., Jungmann, F., Steinborn, M.-M., et al. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-021-00337-8 · Cited by 513
“Unlike classical data secret sharing schemes like SecureNN 29 , where a shared input [[ x ]] is applied on a public function f , FSS applies a public input x on a private shared function Both approaches output a secret shared result.”
MethodInfluentialCrypTFlow2: Practical 2-Party Secure Inference
Rathee, D., Rathee, M., Kumar, N., Chandran, N., Gupta, D., Rastogi, A., & Sharma, R. (2020) · Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3372297.3417274 · Cited by 326
Self-citationPySyft: A Library for Easy Federated Learning
Ziller, A., Trask, A., Lopardo, A., Szymkow, B., Wagner, B., Bluemke, E., Nounahon, J.-M., Passerat-Palmbach, J., Prakash, K., Rose, N., et al. (2021) · Studies in Computational Intelligence · doi:10.1007/978-3-030-70604-3_5 · Cited by 246
CrypTFlow: Secure TensorFlow Inference
Kumar, N., Rathee, M., Chandran, N., Gupta, D., Rastogi, A., & Sharma, R. (2020) · 2020 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp40000.2020.00092 · Cited by 245
Self-citationPOSEIDON: Privacy-Preserving Federated Neural Network Learning
Sav, S., Pyrgelis, A., Troncoso-Pastoriza, J. R., Froelicher, D., Bossuat, J.-P., Sousa, J. S., & Hubaux, J.-P. (2021) · Proceedings 2021 Network and Distributed System Security Symposium · doi:10.14722/ndss.2021.24119 · Cited by 162
Metadata
- Authors
- Wagh, S., Gupta, D., & Chandran, N.
- Venue
- Proceedings on Privacy Enhancing Technologies
- Published
- 2019-07-01
- Volume
- 2019
- Issue
- 3
- Pages
- 26-49
- ISSN
- 2299-0984 (ISSN-L)
- OpenAlex
- W2963752132
- Cited by
- 413
- References
- 34
- FWCI
- 21.87
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.