PINFER: Privacy-Preserving Inference - Logistic Regression, Support Vector Machines, and More, over Encrypted Data

The foreseen growing role of outsourced machine learning services is raising concerns about the privacy of user data. This paper proposes a variety of protocols for privacy-preserving regression and classification that (i) only require additively homomorphic encryption algorithms, (ii) limit interactions to a mere request and response, and (iii) that can be used directly for important machine-learning algorithms such as logistic regression and SVM classification. The basic protocols are then extended and applied to simple feed-forward neural networks.

[1]  Bart Goethals,et al.  On Private Scalar Product Computation for Privacy-Preserving Data Mining , 2004, ICISC.

[2]  Yoshua Bengio,et al.  Deep Sparse Rectifier Neural Networks , 2011, AISTATS.

[3]  Michael Naehrig,et al.  Private Predictive Analysis on Encrypted Medical Data , 2014, IACR Cryptol. ePrint Arch..

[4]  Zoe L. Jiang,et al.  Secure Dot Product of Outsourced Encrypted Vectors and its Application to SVM , 2017, SCC@AsiaCCS.

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

[6]  Thijs Veugen,et al.  Improving the DGK comparison protocol , 2012, 2012 IEEE International Workshop on Information Forensics and Security (WIFS).

[7]  Ivan Damgård,et al.  A correction to 'efficient and secure comparison for on-line auctions' , 2009, Int. J. Appl. Cryptogr..

[8]  Ahmad-Reza Sadeghi,et al.  Efficient Privacy-Preserving Face Recognition , 2009, ICISC.

[9]  Stefan Katzenbeisser,et al.  Privacy-Preserving Face Recognition , 2009, Privacy Enhancing Technologies.

[10]  Shafi Goldwasser,et al.  Machine Learning Classification over Encrypted Data , 2015, NDSS.

[11]  Xiaoqian Jiang,et al.  Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation , 2018, IACR Cryptol. ePrint Arch..

[12]  Yehuda Lindell,et al.  Privacy Preserving Data Mining , 2000, Journal of Cryptology.

[13]  Ran El-Yaniv,et al.  Binarized Neural Networks , 2016, ArXiv.

[14]  Ivan Damgård,et al.  Homomorphic encryption and secure comparison , 2008, Int. J. Appl. Cryptogr..

[15]  Marc Joye,et al.  Private yet Efficient Decision Tree Evaluation , 2018, DBSec.

[16]  Vitaly Feldman,et al.  Privacy-preserving Prediction , 2018, COLT.

[17]  Rakesh Agrawal,et al.  Privacy-preserving data mining , 2000, SIGMOD 2000.

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

[19]  Fan Zhang,et al.  Stealing Machine Learning Models via Prediction APIs , 2016, USENIX Security Symposium.