Privacy-Preserving Wavelet Neural Network with Fully Homomorphic Encryption

vravi@idrbt.ac.in Abstract The main aim of Privacy-Preserving Machine Learning (PPML) is to protect the privacy and provide security to the data used in building Machine Learning models. There are various techniques in PPML such as Secure Multi-Party Computation, Differential Privacy, and Homomorphic Encryption (HE). The techniques are combined with various Machine Learning models and even Deep Learning Networks to protect the data privacy as well as the identity of the user. In this paper, we propose a fully homomorphic encrypted wavelet neural network to protect privacy and at the same time not compromise on the efficiency of the model. We tested the effectiveness of the proposed method on seven datasets taken from the finance and healthcare domains. The results show that our proposed model performs similarly to the unencrypted

[1]  Nathalie Baracaldo,et al.  Privacy-Preserving Machine Learning: Methods, Challenges and Directions , 2021, ArXiv.

[2]  Alaa Eddine Belfedhal,et al.  TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption , 2021, ArXiv.

[3]  Yike Guo,et al.  Privacy preservation in federated learning: An insightful survey from the GDPR perspective , 2020, Comput. Secur..

[4]  Diego Klabjan,et al.  The Impact of the Mini-batch Size on the Variance of Gradients in Stochastic Gradient Descent , 2020, ArXiv.

[5]  Weixin Xie,et al.  Private Machine Learning Classification Based on Fully Homomorphic Encryption , 2020, IEEE Transactions on Emerging Topics in Computing.

[6]  William Stallings,et al.  Handling of Personal Information and Deidentified, Aggregated, and Pseudonymized Information Under the California Consumer Privacy Act , 2020, IEEE Security & Privacy.

[7]  Sharath Pankanti,et al.  Towards Deep Neural Network Training on Encrypted Data , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[8]  Ann Dooms,et al.  Conditionals in Homomorphic Encryption and Machine Learning Applications , 2018, IACR Cryptol. ePrint Arch..

[9]  M. Moraud.  Wavelet Networks , 2018, Foundations of Wavelet Networks and Applications.

[10]  Zhicong Huang,et al.  Logistic regression over encrypted data from fully homomorphic encryption , 2018, BMC Medical Genomics.

[11]  Frederik Vercauteren,et al.  Privacy-preserving logistic regression training , 2018, BMC Medical Genomics.

[12]  Jung Hee Cheon,et al.  Ensemble Method for Privacy-Preserving Logistic Regression Based on Homomorphic Encryption , 2018, IEEE Access.

[13]  Gouenou Coatrieux,et al.  Secure Multilayer Perceptron Based On Homomorphic Encryption , 2018, IWDW.

[14]  Mohammad Al-Rubaie,et al.  Privacy-Preserving Machine Learning: Threats and Solutions , 2018, IEEE Security & Privacy.

[15]  F. Caramelo,et al.  Using Resistin, glucose, age and BMI to predict the presence of breast cancer , 2018, BMC Cancer.

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

[17]  Mohammed Farik,et al.  RSA Public Key Cryptography Algorithm – A Review , 2017 .

[18]  Mauro Conti,et al.  A Survey on Homomorphic Encryption Schemes , 2017, ACM Comput. Surv..

[19]  Abdelkarim Erradi,et al.  Paillier's encryption: Implementation and cloud applications , 2015, 2015 International Conference on Applied Research in Computer Science and Engineering (ICAR).

[20]  Pengtao Xie,et al.  Crypto-Nets: Neural Networks over Encrypted Data , 2014, ArXiv.

[21]  Warren B. Chik,et al.  The Singapore Personal Data Protection Act and an assessment of future trends in data privacy reform , 2013, Comput. Law Secur. Rev..

[22]  Stratis Ioannidis,et al.  Privacy-Preserving Ridge Regression on Hundreds of Millions of Records , 2013, 2013 IEEE Symposium on Security and Privacy.

[23]  David Gil Méndez,et al.  Predicting seminal quality with artificial intelligence methods , 2012, Expert Syst. Appl..

[24]  Vinod Vaikuntanathan,et al.  On-the-fly multiparty computation on the cloud via multikey fully homomorphic encryption , 2012, STOC '12.

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

[26]  Craig Gentry,et al.  Fully Homomorphic Encryption over the Integers , 2010, EUROCRYPT.

[27]  Vadlamani Ravi,et al.  Software development cost estimation using wavelet neural networks , 2008, J. Syst. Softw..

[28]  Ingoo Han,et al.  The discovery of experts' decision rules from qualitative bankruptcy data using genetic algorithms , 2003, Expert Syst. Appl..

[29]  Richard S. Johannes,et al.  Using the ADAP Learning Algorithm to Forecast the Onset of Diabetes Mellitus , 1988 .

[30]  GUOWEI QIU,et al.  Privacy-Preserving Linear Regression on Distributed Data by Homomorphic Encryption and Data Masking , 2020, IEEE Access.

[31]  Shai Halevi,et al.  Design and implementation of HElib: a homomorphic encryption library , 2020, IACR Cryptol. ePrint Arch..

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

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

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

[35]  Hadi Otrok,et al.  A COMPARITIVE STUDY OF ELGAMAL BASED CRYPTOGRAPHIC ALGORITHMS , 2004 .

[36]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..