SwaNN: Switching among Cryptographic Tools for Privacy-preserving Neural Network Predictions

The rise of cloud computing technology led to a paradigm shift in technological services that enabled enterprises to delegate their data analytics tasks to cloud servers which have domain-specific expertise and computational resources for the required analytics. Machine Learning as a Service (MLaaS) is one such service which provides the enterprises to perform machine learning tasks on the cloud. Despite the advantage of eliminating the need for computational resources and domain expertise, sharing sensitive data with the cloud server brings a privacy risk to the enterprises. In this paper, we propose SwaNN, a protocol to privately perform neural network predictions for MLaaS. SwaNN brings together two well-known techniques for secure computation: partially homomorphic encryption and secure two-party computation, and computes neural network predictions by switching between the two methods. The hybrid nature of SwaNN enables to maintain the accuracy of predictions and to optimize the computation time and bandwidth usage. Our experiments show that SwaNN achieves a good balance between computation and communication cost in neural network predictions compared to the state-of-the-art proposals.

[1]  Farinaz Koushanfar,et al.  XONN: XNOR-based Oblivious Deep Neural Network Inference , 2019, IACR Cryptol. ePrint Arch..

[2]  Morten Dahl,et al.  Private Machine Learning in TensorFlow using Secure Computation , 2018, ArXiv.

[3]  Ivan Damgård,et al.  A Generalisation, a Simplification and Some Applications of Paillier's Probabilistic Public-Key System , 2001, Public Key Cryptography.

[4]  Miriam A. M. Capretz,et al.  MLaaS: Machine Learning as a Service , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[5]  Andrew Chi-Chih Yao,et al.  Protocols for Secure Computations (Extended Abstract) , 1982, FOCS.

[6]  Chae Hoon Lim,et al.  More Flexible Exponentiation with Precomputation , 1994, CRYPTO.

[7]  Nicolas Gama,et al.  TFHE: Fast Fully Homomorphic Encryption Over the Torus , 2019, Journal of Cryptology.

[8]  Anantha Chandrakasan,et al.  Gazelle: A Low Latency Framework for Secure Neural Network Inference , 2018, IACR Cryptol. ePrint Arch..

[9]  Tomas Toft.  Sub-linear, Secure Comparison with Two Non-colluding Parties , 2011, Public Key Cryptography.

[10]  Sameer Wagh,et al.  SecureNN: Efficient and Private Neural Network Training , 2018, IACR Cryptol. ePrint Arch..

[11]  Takayuki Ito,et al.  Neocognitron: A neural network model for a mechanism of visual pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[12]  Payman Mohassel,et al.  SecureML: A System for Scalable Privacy-Preserving Machine Learning , 2017, 2017 IEEE Symposium on Security and Privacy (SP).

[13]  Peter Rindal,et al.  ABY3: A Mixed Protocol Framework for Machine Learning , 2018, IACR Cryptol. ePrint Arch..

[14]  Hassan Takabi,et al.  Privacy-preserving Machine Learning as a Service , 2018, Proc. Priv. Enhancing Technol..

[15]  Mauro Barni,et al.  A privacy-preserving protocol for neural-network-based computation , 2006, MM&Sec '06.

[16]  Pascal Paillier,et al.  Fast Homomorphic Evaluation of Deep Discretized Neural Networks , 2018, IACR Cryptol. ePrint Arch..

[17]  Vitaly Shmatikov,et al.  Chiron: Privacy-preserving Machine Learning as a Service , 2018, ArXiv.

[18]  Constance Morel,et al.  Privacy-Preserving Classification on Deep Neural Network , 2017, IACR Cryptol. ePrint Arch..

[19]  Mauro Barni,et al.  Oblivious Neural Network Computing via Homomorphic Encryption , 2007, EURASIP J. Inf. Secur..

[20]  Farinaz Koushanfar,et al.  Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications , 2018, IACR Cryptol. ePrint Arch..

[21]  Yehuda Lindell,et al.  How To Simulate It - A Tutorial on the Simulation Proof Technique , 2016, IACR Cryptol. ePrint Arch..

[22]  Donald Beaver,et al.  Efficient Multiparty Protocols Using Circuit Randomization , 1991, CRYPTO.

[23]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[24]  Nicola Jones,et al.  Computer science: The learning machines , 2014, Nature.

[25]  James Philbin,et al.  FaceNet: A unified embedding for face recognition and clustering , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Hassan Takabi,et al.  CryptoDL: Deep Neural Networks over Encrypted Data , 2017, ArXiv.

[27]  Mauro Barni,et al.  Composite Signal Representation for Fast and Storage-Efficient Processing of Encrypted Signals , 2010, IEEE Transactions on Information Forensics and Security.

[28]  Frederik Vercauteren,et al.  Fully homomorphic SIMD operations , 2012, Designs, Codes and Cryptography.

[29]  Jürgen Schmidhuber,et al.  Multi-column deep neural networks for image classification , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[30]  Silvio Micali,et al.  A Completeness Theorem for Protocols with Honest Majority , 1987, STOC 1987.

[31]  Melek Önen,et al.  FHE-Compatible Batch Normalization for Privacy Preserving Deep Learning , 2018, DPM/CBT@ESORICS.

[32]  Pascal Paillier,et al.  Public-Key Cryptosystems Based on Composite Degree Residuosity Classes , 1999, EUROCRYPT.

[33]  Dan Boneh,et al.  Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware , 2018, ICLR.

[34]  Michael Naehrig,et al.  CryptoNets: applying neural networks to encrypted data with high throughput and accuracy , 2016, ICML 2016.

[35]  Farinaz Koushanfar,et al.  DeepSecure: Scalable Provably-Secure Deep Learning , 2017, 2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC).

[36]  Sebastian Nowozin,et al.  Oblivious Multi-Party Machine Learning on Trusted Processors , 2016, USENIX Security Symposium.

[37]  Li Fei-Fei,et al.  Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference , 2018, ArXiv.

[38]  Ahmad-Reza Sadeghi,et al.  TASTY: tool for automating secure two-party computations , 2010, CCS '10.

[39]  Varun Kanade,et al.  TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service , 2018, ICML.

[40]  Xiaoqian Jiang,et al.  Secure Outsourced Matrix Computation and Application to Neural Networks , 2018, CCS.

[41]  Michael Zohner,et al.  ABY - A Framework for Efficient Mixed-Protocol Secure Two-Party Computation , 2015, NDSS.

[42]  Yao Lu,et al.  Oblivious Neural Network Predictions via MiniONN Transformations , 2017, IACR Cryptol. ePrint Arch..