Privacy Preserving Inference for Deep Neural Networks: Optimizing Homomorphic Encryption for Efficient and Secure Classification
The application of machine learning in healthcare, financial, social media, and other sensitive sectors not only involves high accuracy but privacy as well. Due to the emergence of the Cloud as a computation and one-to-many access paradigm; training and classification/inference tasks have been outso...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10411911/ |
| _version_ | 1797335505247928320 |
|---|---|
| author | Aftab Akram Fawad Khan Shahzaib Tahir Asif Iqbal Syed Aziz Shah Abdullah Baz |
| author_facet | Aftab Akram Fawad Khan Shahzaib Tahir Asif Iqbal Syed Aziz Shah Abdullah Baz |
| author_sort | Aftab Akram |
| collection | DOAJ |
| description | The application of machine learning in healthcare, financial, social media, and other sensitive sectors not only involves high accuracy but privacy as well. Due to the emergence of the Cloud as a computation and one-to-many access paradigm; training and classification/inference tasks have been outsourced to Cloud. However, its usage is limited due to legal and ethical constraints regarding privacy. In this work, we propose a privacy-preserving neural networks-based classification model based on Homomorphic Encryption (HE) where the user can send an encrypted instance to the cloud and receive an encrypted inference from it to preserve the user’s query privacy. In contrast to existing works, we demonstrate the realistic limitations of HE for privacy-preserving machine learning by changing its parameters for enhanced security and accuracy. We showcase scenarios where the choice of HE parameters impedes accurate classification and present an optimized setting for achieving reliable classification. We present several results to demonstrate its effectiveness using MNIST dataset with highly improved inference time for a query as compared to the state of the art. |
| first_indexed | 2024-03-08T08:39:11Z |
| format | Article |
| id | doaj.art-503e72ca482f4492baa13e4ac604e156 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T08:39:11Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-503e72ca482f4492baa13e4ac604e1562024-02-02T00:03:25ZengIEEEIEEE Access2169-35362024-01-0112156841569510.1109/ACCESS.2024.335714510411911Privacy Preserving Inference for Deep Neural Networks: Optimizing Homomorphic Encryption for Efficient and Secure ClassificationAftab Akram0https://orcid.org/0009-0003-2402-4058Fawad Khan1https://orcid.org/0000-0001-6609-5928Shahzaib Tahir2https://orcid.org/0000-0003-4737-0191Asif Iqbal3https://orcid.org/0000-0002-4657-4451Syed Aziz Shah4https://orcid.org/0000-0003-2052-1121Abdullah Baz5https://orcid.org/0000-0002-8669-6883Department of Information Security, College of Signals, National University of Sciences and Technology (NUST), Islamabad, PakistanDepartment of Information Security, College of Signals, National University of Sciences and Technology (NUST), Islamabad, PakistanDepartment of Information Security, College of Signals, National University of Sciences and Technology (NUST), Islamabad, PakistanDepartment of Electrical and Computer Engineering, National University of Singapore, Singapore, Queenstown, SingaporeResearch Centre for Intelligent Healthcare, Coventry University, Coventry, U.K.Department of Computer and Network Engineering, College of Computing, Umm Al-Qura University, Makkah, Saudi ArabiaThe application of machine learning in healthcare, financial, social media, and other sensitive sectors not only involves high accuracy but privacy as well. Due to the emergence of the Cloud as a computation and one-to-many access paradigm; training and classification/inference tasks have been outsourced to Cloud. However, its usage is limited due to legal and ethical constraints regarding privacy. In this work, we propose a privacy-preserving neural networks-based classification model based on Homomorphic Encryption (HE) where the user can send an encrypted instance to the cloud and receive an encrypted inference from it to preserve the user’s query privacy. In contrast to existing works, we demonstrate the realistic limitations of HE for privacy-preserving machine learning by changing its parameters for enhanced security and accuracy. We showcase scenarios where the choice of HE parameters impedes accurate classification and present an optimized setting for achieving reliable classification. We present several results to demonstrate its effectiveness using MNIST dataset with highly improved inference time for a query as compared to the state of the art.https://ieeexplore.ieee.org/document/10411911/Convolutional neural networkhomomorphic encryptionactivation functioncloud serverapproximation techniquessecurity and privacy |
| spellingShingle | Aftab Akram Fawad Khan Shahzaib Tahir Asif Iqbal Syed Aziz Shah Abdullah Baz Privacy Preserving Inference for Deep Neural Networks: Optimizing Homomorphic Encryption for Efficient and Secure Classification IEEE Access Convolutional neural network homomorphic encryption activation function cloud server approximation techniques security and privacy |
| title | Privacy Preserving Inference for Deep Neural Networks: Optimizing Homomorphic Encryption for Efficient and Secure Classification |
| title_full | Privacy Preserving Inference for Deep Neural Networks: Optimizing Homomorphic Encryption for Efficient and Secure Classification |
| title_fullStr | Privacy Preserving Inference for Deep Neural Networks: Optimizing Homomorphic Encryption for Efficient and Secure Classification |
| title_full_unstemmed | Privacy Preserving Inference for Deep Neural Networks: Optimizing Homomorphic Encryption for Efficient and Secure Classification |
| title_short | Privacy Preserving Inference for Deep Neural Networks: Optimizing Homomorphic Encryption for Efficient and Secure Classification |
| title_sort | privacy preserving inference for deep neural networks optimizing homomorphic encryption for efficient and secure classification |
| topic | Convolutional neural network homomorphic encryption activation function cloud server approximation techniques security and privacy |
| url | https://ieeexplore.ieee.org/document/10411911/ |
| work_keys_str_mv | AT aftabakram privacypreservinginferencefordeepneuralnetworksoptimizinghomomorphicencryptionforefficientandsecureclassification AT fawadkhan privacypreservinginferencefordeepneuralnetworksoptimizinghomomorphicencryptionforefficientandsecureclassification AT shahzaibtahir privacypreservinginferencefordeepneuralnetworksoptimizinghomomorphicencryptionforefficientandsecureclassification AT asifiqbal privacypreservinginferencefordeepneuralnetworksoptimizinghomomorphicencryptionforefficientandsecureclassification AT syedazizshah privacypreservinginferencefordeepneuralnetworksoptimizinghomomorphicencryptionforefficientandsecureclassification AT abdullahbaz privacypreservinginferencefordeepneuralnetworksoptimizinghomomorphicencryptionforefficientandsecureclassification |