Efficient Evaluation of Activation Functions over Encrypted Data

We describe a method for approximating any bounded activation function given encrypted input data. The utility of our method is exemplified by simulating it within two typical machine learning tasks: namely, a Variational Autoencoder that learns a latent representation of MNIST data, and an MNIST image classifier.

[1]  Cynthia Dwork,et al.  Differential Privacy , 2006, ICALP.

[2]  B. Barak.  Fully Homomorphic Encryption and Post Quantum Cryptography , 2010 .

[3]  Shai Halevi,et al.  An Improved RNS Variant of the BFV Homomorphic Encryption Scheme , 2019, IACR Cryptol. ePrint Arch..

[4]  Michael Naehrig,et al.  ML Confidential: Machine Learning on Encrypted Data , 2012, ICISC.

[5]  Shashi Narayan,et al.  Privacy-preserving Neural Representations of Text , 2018, EMNLP.

[6]  Craig Gentry,et al.  Fully Homomorphic Encryption with Polylog Overhead , 2012, EUROCRYPT.

[7]  Ronald L. Rivest,et al.  ON DATA BANKS AND PRIVACY HOMOMORPHISMS , 1978 .

[8]  Martín Abadi,et al.  Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data , 2016, ICLR.

[9]  Berk Sunar,et al.  Bandwidth Efficient PIR from NTRU , 2014, Financial Cryptography Workshops.

[10]  Hassan Takabi,et al.  CryptoDL : Towards Deep Learning over Encrypted Data , 2018 .

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

[12]  Dan Feldman,et al.  Secure Search via Multi-Ring Fully Homomorphic Encryption , 2018, IACR Cryptol. ePrint Arch..

[13]  Bhiksha Raj,et al.  Privacy-Preserving Speaker Verification and Identification Using Gaussian Mixture Models , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

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

[15]  Jung Hee Cheon,et al.  Homomorphic Encryption for Arithmetic of Approximate Numbers , 2017, ASIACRYPT.

[16]  Ian Goodfellow,et al.  Deep Learning with Differential Privacy , 2016, CCS.

[17]  Caroline Fontaine,et al.  A Survey of Homomorphic Encryption for Nonspecialists , 2007, EURASIP J. Inf. Secur..

[18]  Úlfar Erlingsson,et al.  Scalable Private Learning with PATE , 2018, ICLR.

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

[20]  Amit Sahai,et al.  Homomorphic Encryption Standard , 2019, IACR Cryptol. ePrint Arch..

[21]  Dan Boneh,et al.  Evaluating 2-DNF Formulas on Ciphertexts , 2005, TCC.

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

[23]  Craig Gentry,et al.  A fully homomorphic encryption scheme , 2009 .

[24]  Max Welling,et al.  Semi-supervised Learning with Deep Generative Models , 2014, NIPS.

[25]  Ron Rothblum,et al.  On the Circular Security of Bit-Encryption , 2013, TCC.

[26]  Zvika Brakerski,et al.  Fully Homomorphic Encryption without Modulus Switching from Classical GapSVP , 2012, CRYPTO.

[27]  Vinod Vaikuntanathan,et al.  Fully Homomorphic Encryption from Ring-LWE and Security for Key Dependent Messages , 2011, CRYPTO.

[28]  Frederik Vercauteren,et al.  Somewhat Practical Fully Homomorphic Encryption , 2012, IACR Cryptol. ePrint Arch..

[29]  Bhiksha Raj,et al.  Privacy preserving probabilistic inference with Hidden Markov Models , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[30]  Yi Su,et al.  Large-scale random forest language models for speech recognition , 2007, INTERSPEECH.

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

[32]  Louis J. M. Aslett,et al.  Encrypted statistical machine learning: new privacy preserving methods , 2015, ArXiv.

[33]  Craig Gentry,et al.  (Leveled) fully homomorphic encryption without bootstrapping , 2012, ITCS '12.