The DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.
ABY 3: A Mixed Protocol Framework for Machine Learning
Abstract
Machine learning is widely used to produce models for a range of applications and is increasingly offered as a service by major technology companies. However, the required massive data collection raises privacy concerns during both training and prediction stages. In this paper, we design and implement a general framework for privacy-preserving machine learning and use it to obtain new solutions for training linear regression, logistic regression and neural network models. Our protocols are in a three-server model wherein data owners secret share their data among three servers who train and evaluate models on the joint data using three-party computation (3PC). Our main contribution is a new and complete framework ($\textABY ^3$) for efficiently switching back and forth between arithmetic, binary, and Yao 3PC which is of independent interest. Many of the conversions are based on new techniques that are designed and optimized for the first time in this paper. We also propose new techniques for fixed-point multiplication of shared decimal values that extends beyond the three-party case, and customized protocols for evaluating piecewise polynomial functions. We design variants of each building block that is secure against \em malicious adversaries who deviate arbitrarily. We implement our system in C++. Our protocols are up to \em four orders of magnitude faster than the best prior work, hence significantly reducing the gap between privacy-preserving and plaintext training.
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
Lecture Notes in Computer Science 1205
(1999) · Industrial Robot: An International Journal · doi:10.1108/ir.1999.04926fae.001 · Cited by 38,662
Deep 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
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
Two-Point Step Size Gradient Methods
BARZILAI, J., & BORWEIN, J. M. (1988) · IMA Journal of Numerical Analysis · doi:10.1093/imanum/8.1.141 · Cited by 2,873
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 2×
“Shokri and Shmatikov [50] propose a solution where instead of sharing the data, the two servers share the changes on a portion of the coefficients during the training.”
BackgroundSecureML: 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
Self-citation(2004) · IEEE Security & Privacy Magazine · doi:10.1109/msp.2004.9 · Cited by 1,518
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
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
Stealing Machine Learning Models via Prediction APIs
Tramèr, F., Zhang, F., Juels, A., Reiter, M. K., & Ristenpart, T. (2016) · arXiv · doi:10.48550/arxiv.1609.02943 · Cited by 796
Privacy preserving auctions and mechanism design
Naor, M., Pinkas, B., & Sumner, R. (1999) · Proceedings of the 1st ACM conference on Electronic commerce · doi:10.1145/336992.337028 · Cited by 753
Improved Garbled Circuit: Free XOR Gates and Applications
Kolesnikov, V., & Schneider, T. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-70583-3_40 · Cited by 743
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 Models that Remember Too Much
Song, C., Ristenpart, T., & Shmatikov, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134077 · Cited by 526 · cited 1×
“These are strong guarantees that, though do not provide a full-proof privacy solution (the models themselves or interactions with them can leak information about the data [51, 53, 55]), provide a strong first line of defense which can be strengthened when combined with orthogonal mechanisms such as differential privac…”
BackgroundFairplayMP: a system for secure multi-party computation
Ben-David, A., Nisan, N., & Pinkas, B. (2008) · Proceedings of the 15th ACM conference on Computer and communications security · doi:10.1145/1455770.1455804 · Cited by 475
Privacy-Preserving Ridge Regression on Hundreds of Millions of Records
Nikolaenko, V., Weinsberg, U., Ioannidis, S., Joye, M., Boneh, D., & Taft, N. (2013) · 2013 IEEE Symposium on Security and Privacy · doi:10.1109/sp.2013.30 · Cited by 439
Privacy-preserving distributed k-means clustering over arbitrarily partitioned data
Jagannathan, G., & Wright, R. N. (2005) · Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining · doi:10.1145/1081870.1081942 · Cited by 420
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
Privacy-Preserving Multivariate Statistical Analysis: Linear Regression and Classification
Du, W., Han, Y. S., & Chen, S. (2004) · Proceedings of the 2004 SIAM International Conference on Data Mining · doi:10.1137/1.9781611972740.21 · Cited by 366
CryptoDL: Deep Neural Networks over Encrypted Data
Hesamifard, E., Takabi, H., & Ghasemi, M. (2017) · arXiv · doi:10.48550/arxiv.1711.05189 · Cited by 306
Fast Homomorphic Evaluation of Deep Discretized Neural Networks
Bourse, F., Minelli, M., Minihold, M., & Paillier, P. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-96878-0_17 · Cited by 300
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
Secure two-party k-means clustering
Bunn, P., & Ostrovsky, R. (2007) · Proceedings of the 14th ACM conference on Computer and communications security · doi:10.1145/1315245.1315306 · Cited by 220
TinyGarble: Highly Compressed and Scalable Sequential Garbled Circuits
Songhori, E. M., Hussain, S. U., Sadeghi, A.-R., Schneider, T., & Koushanfar, F. (2015) · 2015 IEEE Symposium on Security and Privacy · doi:10.1109/sp.2015.32 · Cited by 210
Privacy-Preserving SVM Classification on Vertically Partitioned Data
Yu, H., Vaidya, J., & Jiang, X. (2006) · Lecture Notes in Computer Science · doi:10.1007/11731139_74 · Cited by 192
Scalable and Secure Logistic Regression via Homomorphic Encryption
Aono, Y., Hayashi, T., Trieu Phong, L., & Wang, L. (2016) · Proceedings of the Sixth ACM Conference on Data and Application Security and Privacy · doi:10.1145/2857705.2857731 · Cited by 179
Privacy-preserving SVM classification
Vaidya, J., Yu, H., & Jiang, X. (2008) · Knowledge and Information Systems · doi:10.1007/s10115-007-0073-7 · Cited by 178
DeepSecure: Scalable Provably-Secure Deep Learning
Rouhani, B. D., Riazi, M. S., & Koushanfar, F. (2018) · 2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC) · doi:10.1109/dac.2018.8465894 · Cited by 176
Privacy-preserving cooperative scientific computations
Du, W., & Atallah, M. J. (2005) · Proceedings. 14th IEEE Computer Security Foundations Workshop, 2001. · doi:10.1109/csfw.2001.930152 · Cited by 166
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
Privacy preserving regression modelling via distributed computation
Sanil, A. P., Karr, A. F., Lin, X., & Reiter, J. P. (2004) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1014052.1014139 · Cited by 147
Deploying Secure Multi-Party Computation for Financial Data Analysis
Bogdanov, D., Talviste, R., & Willemson, J. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32946-3_5 · Cited by 116
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
Self-citationTwo Halves Make a Whole: Reducing Data Transfer in Garbled Circuits using Half Gates.
Zahur, S., Rosulek, M., & Evans, D. (2014) · Cited by 112
Efficient Mining of Frequent Patterns from Uncertain Data
Leung, C. K.-S., Carmichael, C. L., & Hao, B. (2007) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw.2007.84 · Cited by 103
Secure Linear Regression on Vertically Partitioned Datasets.Preprint
Gascón, A., Schoppmann, P., Balle, B., Raykova, M., Doerner, J., Zahur, S., & Evans, D. (2016) · IACR Cryptology ePrint Archive · Cited by 92
Private Collaborative Neural Network Learning.Preprint
Chase, M., Gilad-Bachrach, R., Laine, K., Lauter, K., & Rindal, P. (2017) · IACR Cryptology ePrint Archive · Cited by 52
Self-citationCompiling Low Depth Circuits for Practical Secure Computation
Büscher, N., Holzer, A., Weber, A., & Katzenbeisser, S. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-45741-3_5 · Cited by 32
Application-Scale Secure Multiparty Computation
Launchbury, J., Archer, D., DuBuisson, T., & Mertens, E. (2014) · Lecture notes in computer science · doi:10.1007/978-3-642-54833-8_2 · Cited by 26
Gilad-Bachrach, R., Laine, K., Lauter, K., Rindal, P., & Rosulek, M. (2019) · Cloud Computing Security Workshop · doi:10.1145/3338466.3358924 · Cited by 23
Self-citationPrivacy-preservation for Stochastic Gradient Descent Application to Secure Logistic Regression
Wu, S., Teruya, T., & Kawamoto, J. (2013) · 人工知能学会全国大会論文集 · Cited by 19
Efficient, Constant-Round and Actively Secure MPC
Chandran, N., Garay, J. A., Mohassel, P., & Vusirikala, S. (2017) · ACM SIGSAC Conference on Computer and Communications Security (CCS) · doi:10.1145/3133956.3134100 · Cited by 14
Self-citationKumaresan, R., Raghuraman, S., & Sealfon, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-662-53008-5_13 · Cited by 6
Cited by
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
A secure federated transfer learning framework
Liu, Y., Kang, Y., Xing, C., Chen, T., & Yang, Q. (2020) · IEEE Intelligent Systems · doi:10.1109/mis.2020.2988525 · Cited by 645
Secure Federated Transfer Learning
Liu, Y., Kang, Y., Xing, C., Chen, T., & Yang, Q. (2018) · arXiv · doi:10.48550/arxiv.1812.03337 · Cited by 645
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · arXiv · doi:10.48550/arxiv.1902.04885 · Cited by 600
Privacy and Robustness in Federated Learning: Attacks and Defenses
Lyu, L., Yu, H., Ma, X., Chen, C., Sun, L., Zhao, J., Yang, Q., & Yu, P. S. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3216981 · Cited by 548
“need to be carefully designed and implemented for each operation in the target learning algorithm [107], [108].”
Background
Metadata
- Authors
- Mohassel, P., & Rindal, P.
- Venue
- Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security
- Publisher
- ACM
- Published
- 2018-10-15
- Pages
- 35-52
- OpenAlex
- W2895865029
- Cited by
- 432
- References
- 47
- FWCI
- 21.74
- 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.