short-paper

MP2ML: A Mixed-Protocol Machine Learning Framework for Private Inference

Authors:

Rosario Cammarota,

Daniel Demmler,

Thomas Schneider,

Hossein YalameAuthors Info & Claims

PPMLP'20: Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice

Pages 43 - 45

https://doi.org/10.1145/3411501.3419425

Published: 09 November 2020 Publication History

Abstract

We present an extended abstract of MP2ML, a machine learning framework which integrates Intel nGraph-HE, a homomorphic encryption (HE) framework, and the secure two-party computation framework ABY, to enable data scientists to perform private inference of deep learning (DL) models trained using popular frameworks such as TensorFlow at the push of a button. We benchmark MP2ML on the CryptoNets network with ReLU activations, on which it achieves a throughput of 33.3 images/s and an accuracy of 98.6%. This throughput matches the previous state-of-the-art frameworks.

References

[1]

Nitin Agrawal, Ali Shahin Shamsabadi, Matt J Kusner, and Adrià Gascón. 2019. QUOTIENT: Two-Party Secure Neural Network Training and Prediction. In CCS'19 .

Digital Library

[2]

Fabian Boemer, Rosario Cammarota, Daniel Demmler, Thomas Schneider, and Hossein Yalame. 2020. MP2ML: A Mixed-Protocol Machine Learning Framework for Private Inference. In ARES'20.

[3]

Fabian Boemer, Anamaria Costache, Rosario Cammarota, and Casimir Wierzynski. 2019 a. nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data. In WAHC'19.

Digital Library

[4]

Fabian Boemer, Yixing Lao, Rosario Cammarota, and Casimir Wierzynski. 2019 b. nGraph-HE: a graph compiler for deep learning on homomorphically encrypted data. In ACM International Conference on Computing Frontiers.

Digital Library

[5]

Jung Hee Cheon, Andrey Kim, Miran Kim, and Yongsoo Song. 2017. Homomorphic Encryption for Arithmetic of Approximate Numbers. In ASIACRYPT'17.

[6]

Daniel Demmler, Thomas Schneider, and Michael Zohner. 2015. ABY - A Framework for Efficient Mixed-Protocol Secure Two-Party Computation. In NDSS'15.

[7]

Ran Gilad-Bachrach, Nathan Dowlin, Kim Laine, Kristin Lauter, Michael Naehrig, and John Wernsing. 2016. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In ICML'16.

[8]

Oded Goldreich, Silvio Micali, and Avi Wigderson. 1987. How to play any mental game. In STOC'87.

Digital Library

[9]

Wilko Henecka, Stefan Kögl, Ahmad-Reza Sadeghi, Thomas Schneider, and Immo Wehrenberg. 2010. TASTY: Tool for Automating Secure Two-party Computations. In CCS'10.

Digital Library

[10]

Ehsan Hesamifard, Hassan Takabi, Mehdi Ghasemi, and Rebecca N. Wright. 2018. Privacy-preserving Machine Learning as a Service. PETS'18.

[11]

Chiraag Juvekar, Vinod Vaikuntanathan, and Anantha Chandrakasan. 2018. GAZELLE: A Low Latency Framework for Secure Neural Network Inference. In USENIX Security'18.

[12]

Nishant Kumar, Mayank Rathee, Nishanth Chandran, Divya Gupta, Aseem Rastogi, and Rahul Sharma. 2020. CrypTFlow: Secure TensorFlow Inference. In S&P'20.

[13]

Jian Liu, Mika Juuti, Yao Lu, and Nadarajah Asokan. 2017. Oblivious neural network predictions via MiniONN transformations. In CCS'17.

Digital Library

[14]

Pratyush Mishra, Ryan Lehmkuhl, Akshayaram Srinivasan, Wenting Zheng, and Raluca Ada Popa. 2020. DELPHI: A Cryptographic Inference Service for Neural Networks. In USENIX Security.

[15]

Payman Mohassel and Yupeng Zhang. 2017. SecureML: A system for scalable privacy-preserving machine learning. In S&P'17 .

[16]

M Sadegh Riazi, Mohammad Samragh, Hao Chen, Kim Laine, Kristin E Lauter, and Farinaz Koushanfar. 2019. XONN: XNOR-based Oblivious Deep Neural Network Inference. In USENIX Security'19.

[17]

M Sadegh Riazi, Christian Weinert, Oleksandr Tkachenko, Ebrahim M Songhori, Thomas Schneider, and Farinaz Koushanfar. 2018. Chameleon: A hybrid secure computation framework for machine learning applications. In ASIACCS'18.

Digital Library

[18]

Ronald L. Rivest, Len Adleman, and Michael L. Dertouzos. 1978. On Data Banks and Privacy Homomorphisms. Foundations of Secure Computation, Academia Press.

[19]

SEAL 2019. Microsoft SEAL (release 3.4). https://github.com/Microsoft/SEAL. Microsoft Research, Redmond, WA.

[20]

Sameer Wagh, Divya Gupta, and Nishanth Chandran. 2019. SecureNN: 3-Party Secure Computation for Neural Network Training. PETS'19.

Cited By

Chen JYang LWu WLiu YFeng Y(2025)Homomorphic Matrix Operations Under Bicyclic EncodingIEEE Transactions on Information Forensics and Security10.1109/TIFS.2024.349086220(1390-1404)Online publication date: 2025
https://doi.org/10.1109/TIFS.2024.3490862
Ben-Itzhak YMöllering HPinkas BSchneider TSuresh ATkachenko OVargaftik SWeinert CYalame HYanai A(2024)ScionFL: Efficient and Robust Secure Quantized Aggregation2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)10.1109/SaTML59370.2024.00031(490-511)Online publication date: 9-Apr-2024
https://doi.org/10.1109/SaTML59370.2024.00031
Brüggemann ASchick OSchneider TSuresh AYalame H(2024)Don’t Eject the Impostor: Fast Three-Party Computation With a Known Cheater2024 IEEE Symposium on Security and Privacy (SP)10.1109/SP54263.2024.00164(503-522)Online publication date: 19-May-2024
https://doi.org/10.1109/SP54263.2024.00164
Show More Cited By

Index Terms

MP2ML: A Mixed-Protocol Machine Learning Framework for Private Inference
1. Computing methodologies
  1. Machine learning
2. Security and privacy
  1. Security services
    1. Privacy-preserving protocols

Recommendations

MP2ML: a mixed-protocol machine learning framework for private inference
ARES '20: Proceedings of the 15th International Conference on Availability, Reliability and Security

Privacy-preserving machine learning (PPML) has many applications, from medical image classification and anomaly detection to financial analysis. nGraph-HE enables data scientists to perform private inference of deep learning (DL) models trained using ...
Cryptography of Blockchain
Smart Computing and Communication
Abstract
With the development of digital currencies and 5G technology, blockchain has gained widespread attention and is being used in areas such as healthcare, industry and smart vehicles. Many security issues have also been exposed in the course of ...
Practical and secure solutions for integer comparison
PKC'07: Proceedings of the 10th international conference on Practice and theory in public-key cryptography

Yao's classical millionaires' problem is about securely determining whether x > y, given two input values x, y, which are held as private inputs by two parties, respectively. The output x > y becomes known to both parties.

In this paper, we consider a ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

PPMLP'20: Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice

November 2020

75 pages

ISBN:9781450380881

DOI:10.1145/3411501

Program Chairs:
Benyu Zhang
Ant Group, USA
,
Raluca Ada Popa
UC Berkeley, USA
,
Matei Zaharia
Stanford University, USA
,
Guofei Gu
Texas A&M University, USA
,
Shouling Ji
Zhejiang University, China

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGSAC: ACM Special Interest Group on Security, Audit, and Control

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 09 November 2020

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Conference

CCS '20

Sponsor:

SIGSAC

CCS '20: 2020 ACM SIGSAC Conference on Computer and Communications Security

November 9, 2020

Virtual Event, USA

Upcoming Conference

CCS '25

Sponsor:
sigsac

ACM SIGSAC Conference on Computer and Communications Security

October 13 - 17, 2025

Taipei , Taiwan

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

18
Total Citations
View Citations
109
Total Downloads

Downloads (Last 12 months)14
Downloads (Last 6 weeks)4

Reflects downloads up to 12 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Chen JYang LWu WLiu YFeng Y(2025)Homomorphic Matrix Operations Under Bicyclic EncodingIEEE Transactions on Information Forensics and Security10.1109/TIFS.2024.349086220(1390-1404)Online publication date: 2025
https://doi.org/10.1109/TIFS.2024.3490862
Ben-Itzhak YMöllering HPinkas BSchneider TSuresh ATkachenko OVargaftik SWeinert CYalame HYanai A(2024)ScionFL: Efficient and Robust Secure Quantized Aggregation2024 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)10.1109/SaTML59370.2024.00031(490-511)Online publication date: 9-Apr-2024
https://doi.org/10.1109/SaTML59370.2024.00031
Brüggemann ASchick OSchneider TSuresh AYalame H(2024)Don’t Eject the Impostor: Fast Three-Party Computation With a Known Cheater2024 IEEE Symposium on Security and Privacy (SP)10.1109/SP54263.2024.00164(503-522)Online publication date: 19-May-2024
https://doi.org/10.1109/SP54263.2024.00164
Pang QZhu JMöllering HZheng WSchneider T(2024)BOLT: Privacy-Preserving, Accurate and Efficient Inference for Transformers2024 IEEE Symposium on Security and Privacy (SP)10.1109/SP54263.2024.00130(4753-4771)Online publication date: 19-May-2024
https://doi.org/10.1109/SP54263.2024.00130
Baruch MDrucker NEzov GGoldberg YKushnir ELerner JSoceanu OZimerman I(2024)Polynomial Adaptation of Large-Scale CNNs for Homomorphic Encryption-Based Secure InferenceCyber Security, Cryptology, and Machine Learning10.1007/978-3-031-76934-4_1(3-25)Online publication date: 12-Dec-2024
https://doi.org/10.1007/978-3-031-76934-4_1
Gehlhar TMarx FSchneider TSuresh AWehrle TYalame H(2023)SafeFL: MPC-friendly Framework for Private and Robust Federated Learning2023 IEEE Security and Privacy Workshops (SPW)10.1109/SPW59333.2023.00012(69-76)Online publication date: May-2023
https://doi.org/10.1109/SPW59333.2023.00012
Brüggemann AHundt RSchneider TSuresh AYalame H(2023)FLUTE: Fast and Secure Lookup Table Evaluations2023 IEEE Symposium on Security and Privacy (SP)10.1109/SP46215.2023.10179345(515-533)Online publication date: May-2023
https://doi.org/10.1109/SP46215.2023.10179345
Drucker NMoshkowich GPelleg TShaul H(2023)BLEACH: Cleaning Errors in Discrete Computations Over CKKSJournal of Cryptology10.1007/s00145-023-09483-137:1Online publication date: 1-Nov-2023
https://dl.acm.org/doi/10.1007/s00145-023-09483-1
Novikova EFomichov DKholod IFilippov E(2022)Analysis of Privacy-Enhancing Technologies in Open-Source Federated Learning Frameworks for Driver Activity RecognitionSensors10.3390/s2208298322:8(2983)Online publication date: 13-Apr-2022
https://doi.org/10.3390/s22082983
Rechberger CWalch R(2022)Privacy-Preserving Machine Learning Using CryptographySecurity and Artificial Intelligence10.1007/978-3-030-98795-4_6(109-129)Online publication date: 8-Apr-2022
https://doi.org/10.1007/978-3-030-98795-4_6
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten