Efficient machine learning over encrypted data with non-interactive communication

Abstract In this paper, we describe a protocol framework that can perform classification tasks in a privacy-preserving manner. To demonstrate the feasibility of the proposed framework, we implement two protocols supporting Naive Bayes classification. We overcome the heavy computational load of conventional fully homomorphic encryption-based privacy-preserving protocols by using various optimization techniques. The proposed method differs from previous techniques insofar as it requires no intermediate interactions between the server and the client while executing the protocol, except for the mandatory interaction to obtain the decryption result of the encrypted classification output. As a result of this minimal interaction, the proposed method is relatively stable. Furthermore, the decryption key is used only once during the execution of the protocol, overcoming a potential security issue caused by the frequent exposure of the decryption key in memory. The proposed implementation uses a cryptographic primitive that is secure against attacks with quantum computers. Therefore, the framework described in this paper is expected to be robust against future quantum computer attacks.

[1]  Hyunsoo Yoon,et al.  Sorting Method for Fully Homomorphic Encrypted Data Using the Cryptographic Single-Instruction Multiple-Data Operation , 2016, IEICE transactions on communications.

[2]  Oded Goldreich,et al.  Foundations of Cryptography: Volume 2, Basic Applications , 2004 .

[3]  Oded Goldreich.  Foundations of Cryptography: Index , 2001 .

[4]  Joshua C. Denny,et al.  The disclosure of diagnosis codes can breach research participants' privacy , 2010, J. Am. Medical Informatics Assoc..

[5]  Andrew McCallum,et al.  A comparison of event models for naive bayes text classification , 1998, AAAI 1998.

[6]  Oded Goldreich,et al.  Foundations of Cryptography: Volume 1, Basic Tools , 2001 .

[7]  Klaus Wehrle,et al.  Choose Wisely: A Comparison of Secure Two-Party Computation Frameworks , 2015, 2015 IEEE Security and Privacy Workshops.

[8]  S. Halevi,et al.  Design and Implementation of a Homomorphic-Encryption Library , 2012 .

[9]  Sebastian Tschiatschek,et al.  Bayesian Network Classifiers with Reduced Precision Parameters , 2012, ECML/PKDD.

[10]  Craig Gentry,et al.  Fully homomorphic encryption using ideal lattices , 2009, STOC '09.

[11]  Jean-Sébastien Coron,et al.  Advances in Cryptology - EUROCRYPT 2017 - 36th Annual International Conference on the Theory and Applications of Cryptographic Techniques, Paris, France, April 30 - May 4, 2017, Proceedings, Part II , 2017, International Conference on the Theory and Application of Cryptographic Techniques.

[12]  N. Lavrac,et al.  Intelligent Data Analysis in Medicine and Pharmacology , 1997 .

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

[14]  Silvio Micali,et al.  How to play ANY mental game , 1987, STOC.

[15]  Niv Gilboa,et al.  Two Party RSA Key Generation , 1999, CRYPTO.

[16]  Younho Lee,et al.  Implementation and Performance Enhancement of Arithmetic Adder for Fully Homomorphic Encrypted Data , 2017 .

[17]  Marco Brambilla,et al.  Asynchronous Web Services Communication Patterns in Business Protocols , 2005, WISE.

[18]  Berk Sunar,et al.  Homomorphic AES evaluation using the modified LTV scheme , 2016, Des. Codes Cryptogr..

[19]  Oded Goldreich.  Foundations of Cryptography: Volume 1 , 2006 .

[20]  Oded Goldreich,et al.  Foundations of Cryptography: List of Figures , 2001 .

[21]  Charu C. Aggarwal,et al.  On the design and quantification of privacy preserving data mining algorithms , 2001, PODS.

[22]  Craig Gentry,et al.  Homomorphic Evaluation of the AES Circuit , 2012, IACR Cryptol. ePrint Arch..

[23]  Kartik Nayak,et al.  ObliVM: A Programming Framework for Secure Computation , 2015, 2015 IEEE Symposium on Security and Privacy.

[24]  Yehuda Lindell,et al.  More efficient oblivious transfer and extensions for faster secure computation , 2013, CCS.

[25]  Silvio Micali,et al.  Probabilistic Encryption , 1984, J. Comput. Syst. Sci..

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

[27]  Andrew Chi-Chih Yao,et al.  Protocols for secure computations , 1982, FOCS 1982.

[28]  Dan Boneh,et al.  Breaking RSA May Not Be Equivalent to Factoring , 1998, EUROCRYPT.

[29]  Chris Peikert,et al.  Λολ: Functional Lattice Cryptography , 2016, CCS.

[30]  Joseph L. Hellerstein,et al.  Recognizing End-User Transactions in Performance Management , 2000, AAAI/IAAI.

[31]  Nicolas Gama,et al.  Improving TFHE: faster packed homomorphic operations and efficient circuit bootstrapping , 2017, IACR Cryptol. ePrint Arch..

[32]  Martin R. Albrecht.  On Dual Lattice Attacks Against Small-Secret LWE and Parameter Choices in HElib and SEAL , 2017, EUROCRYPT.

[33]  Jun Sakuma,et al.  Using Fully Homomorphic Encryption for Statistical Analysis of Categorical, Ordinal and Numerical Data , 2016, NDSS.

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

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

[36]  Dan Boneh,et al.  The Decision Diffie-Hellman Problem , 1998, ANTS.

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

[38]  Benny Pinkas,et al.  Fairplay - Secure Two-Party Computation System , 2004, USENIX Security Symposium.

[39]  Blaz Zupan,et al.  Predictive data mining in clinical medicine: Current issues and guidelines , 2008, Int. J. Medical Informatics.

[40]  Houkuan Huang,et al.  Feature selection for text classification with Naïve Bayes , 2009, Expert Syst. Appl..

[41]  Philip S. Yu,et al.  A General Survey of Privacy-Preserving Data Mining Models and Algorithms , 2008, Privacy-Preserving Data Mining.

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

[43]  Erik Lux.  Feature selection for text classification with Naive Bayes , 2012 .

[45]  Berk Sunar,et al.  Depth Optimized Efficient Homomorphic Sorting , 2015, LATINCRYPT.

[46]  Jianfeng Ma,et al.  Privacy-Preserving Patient-Centric Clinical Decision Support System on Naïve Bayesian Classification , 2016, IEEE Journal of Biomedical and Health Informatics.

[47]  Mihir Bellare,et al.  The Security of Triple Encryption and a Framework for Code-Based Game-Playing Proofs , 2006, EUROCRYPT.

[48]  Chris Peikert,et al.  On Ideal Lattices and Learning with Errors over Rings , 2010, EUROCRYPT.

[49]  Somesh Jha,et al.  Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures , 2015, CCS.

[50]  Irina Rish,et al.  An empirical study of the naive Bayes classifier , 2001 .

[51]  M. Bonten,et al.  treatment of , 2004 .

[52]  ASHWIN MACHANAVAJJHALA,et al.  L-diversity: privacy beyond k-anonymity , 2006, 22nd International Conference on Data Engineering (ICDE'06).

[53]  Shai Halevi,et al.  Bootstrapping for HElib , 2015, EUROCRYPT.

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

[55]  Igor Kononenko,et al.  Machine learning for medical diagnosis: history, state of the art and perspective , 2001, Artif. Intell. Medicine.

[56]  Anderson C. A. Nascimento,et al.  Efficient and Private Scoring of Decision Trees, Support Vector Machines and Logistic Regression Models Based on Pre-Computation , 2019, IEEE Transactions on Dependable and Secure Computing.

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

[58]  Anderson C. A. Nascimento,et al.  Efficient Unconditionally Secure Comparison and Privacy Preserving Machine Learning Classification Protocols , 2015, ProvSec.

[59]  Michael Naehrig,et al.  Privately Evaluating Decision Trees and Random Forests , 2016, IACR Cryptol. ePrint Arch..

[60]  Vinod Vaikuntanathan,et al.  SHIELD: Scalable Homomorphic Implementation of Encrypted Data-Classifiers , 2015, IEEE Transactions on Computers.

[61]  Elpida T. Keravnou,et al.  Intelligent Data Analysis for Medical Diagnosis: Using Machine Learning and Temporal Abstraction , 1998, AI Commun..

[62]  Simon Knowles,et al.  A family of adders , 1999, Proceedings 14th IEEE Symposium on Computer Arithmetic (Cat. No.99CB36336).

[63]  Shai Halevi,et al.  Algorithms in HElib , 2014, CRYPTO.

[64]  Benny Pinkas,et al.  FairplayMP: a system for secure multi-party computation , 2008, CCS.

[65]  Craig Gentry,et al.  (Leveled) Fully Homomorphic Encryption without Bootstrapping , 2014, ACM Trans. Comput. Theory.

[66]  John B. Shoven,et al.  I , Edinburgh Medical and Surgical Journal.