Fabian Boemer
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.
- Nitin Agrawal, Ali Shahin Shamsabadi, Matt J Kusner, and Adrià Gascón. 2019. QUOTIENT: Two-Party Secure Neural Network Training and Prediction. In CCS'19 .Google Scholar
Digital Library
- 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.Google Scholar
- 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.Google ScholarDigital Library
- 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.Google ScholarDigital Library
- Jung Hee Cheon, Andrey Kim, Miran Kim, and Yongsoo Song. 2017. Homomorphic Encryption for Arithmetic of Approximate Numbers. In ASIACRYPT'17.Google Scholar
- Daniel Demmler, Thomas Schneider, and Michael Zohner. 2015. ABY - A Framework for Efficient Mixed-Protocol Secure Two-Party Computation. In NDSS'15.Google Scholar
- 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.Google Scholar
- Oded Goldreich, Silvio Micali, and Avi Wigderson. 1987. How to play any mental game. In STOC'87.Google ScholarDigital Library
- Wilko Henecka, Stefan Kögl, Ahmad-Reza Sadeghi, Thomas Schneider, and Immo Wehrenberg. 2010. TASTY: Tool for Automating Secure Two-party Computations. In CCS'10.Google ScholarDigital Library
- Ehsan Hesamifard, Hassan Takabi, Mehdi Ghasemi, and Rebecca N. Wright. 2018. Privacy-preserving Machine Learning as a Service. PETS'18.Google Scholar
- Chiraag Juvekar, Vinod Vaikuntanathan, and Anantha Chandrakasan. 2018. GAZELLE: A Low Latency Framework for Secure Neural Network Inference. In USENIX Security'18.Google Scholar
- Nishant Kumar, Mayank Rathee, Nishanth Chandran, Divya Gupta, Aseem Rastogi, and Rahul Sharma. 2020. CrypTFlow: Secure TensorFlow Inference. In S&P'20.Google Scholar
- Jian Liu, Mika Juuti, Yao Lu, and Nadarajah Asokan. 2017. Oblivious neural network predictions via MiniONN transformations. In CCS'17.Google ScholarDigital Library
- Pratyush Mishra, Ryan Lehmkuhl, Akshayaram Srinivasan, Wenting Zheng, and Raluca Ada Popa. 2020. DELPHI: A Cryptographic Inference Service for Neural Networks. In USENIX Security.Google Scholar
- Payman Mohassel and Yupeng Zhang. 2017. SecureML: A system for scalable privacy-preserving machine learning. In S&P'17 .Google Scholar
- 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.Google Scholar
- 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.Google ScholarDigital Library
- Ronald L. Rivest, Len Adleman, and Michael L. Dertouzos. 1978. On Data Banks and Privacy Homomorphisms. Foundations of Secure Computation, Academia Press.Google Scholar
- SEAL 2019. Microsoft SEAL (release 3.4). https://github.com/Microsoft/SEAL. Microsoft Research, Redmond, WA.Google Scholar
- Sameer Wagh, Divya Gupta, and Nishanth Chandran. 2019. SecureNN: 3-Party Secure Computation for Neural Network Training. PETS'19.Google ScholarCross Ref
Index Terms
- MP2ML: A Mixed-Protocol Machine Learning Framework for Private Inference
Recommendations
MP2ML: a mixed-protocol machine learning framework for private inference
ARES '20: Proceedings of the 15th International Conference on Availability, Reliability and SecurityPrivacy-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 CommunicationAbstractWith 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 cryptographyYao'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