Citation:

Ranadeep Palle, Dr. A. Punitha 2021. "Privacy-Preserving Homomorphic Encryption Schemes for Machine Learning in the Cloud" ESP Journal of Engineering & Technology Advancements  1(2): 24-33.

Abstract:

This examination investigates the joining of protection safeguarding homomorphic encryption plans in cloud-based AI to address blossoming concerns regarding information security and protection. This proposed method is based on recent contributions and focuses on tailoring homomorphic encryption algorithms like Paillier and Fully Homomorphic Encryption (FHE) to specific machine learning tasks. To strike a balance between data utility and privacy, seamless compatibility with preprocessing pipelines is prioritized. Secure model preparation strategies, consolidating cryptographic conventions and secure conglomeration techniques, are crucial in saving the secrecy of delicate data. The improvement of encoded model assessment measurements guarantees a hearty evaluation of model execution without compromising protection. Our technique stretches out to strengthening the general security act through exhaustive examination and countermeasure execution, tending to likely weaknesses in homomorphic encryption. Coordination inside the cloud foundation is a focal subject, with an emphasis on versatility, similarity, and true relevance. Challenges connected with dormancy, asset utilization, and versatility to fluctuating jobs are addressed to exhibit the down-to-earth practicality of security safeguarding AI. Looking forward, future work ought to envelop headways in encryption calculations, client-driven contemplations, cooperation with industry partners, and novel applications in united learning and IoT situations.

References:

[1] Y. Bai et al, "cuSCNN: A Secure and Batch-Processing Framework for Privacy-Preserving Convolutional Neural Network Prediction on GPU," Frontiers in Computational Neuroscience, 2021. Available: https://www.proquest.com/scholarly-journals/cuscnn-secure-batch-processing-framework-privacy/docview/2612984974/se-2. DOI: https://doi.org/10.3389/fncom.2021.799977.

[2] Y. Son et al, "Privacy-preserving breast cancer recurrence prediction based on homomorphic encryption and secure two party computation," PLoS One, vol. 16, (12), 2021. Available: https://www.proquest.com/scholarly-journals/privacy-preserving-breast-cancer-recurrence/docview/2612008839/se-2. DOI: https://doi.org/10.1371/journal.pone.0260681.

[3] L. Zhang, Z. Zehui and G. Cong, "Accelerating privacy-preserving momentum federated learning for industrial cyber-physical systems," Complex & Intelligent Systems, vol. 7, (6), pp. 3289-3301, 2021. Available: https://www.proquest.com/scholarly-journals/accelerating-privacy-preserving-momentum/docview/2588792677/se-2. DOI: https://doi.org/10.1007/s40747-021-00519-2.

[4] S. Sharma and K. Chen, "Confidential machine learning on untrusted platforms: a survey," Cybersecurity, vol. 4, (1), 2021. Available: https://www.proquest.com/scholarly-journals/confidential-machine-learning-on-untrusted/docview/2567803602/se-2. DOI: https://doi.org/10.1186/s42400-021-00092-8.

[5] S. A. Ala, B. Kane and S. Fischer-Hübner, "Machine Learning–Based Analysis of Encrypted Medical Data in the Cloud: Qualitative Study of Expert Stakeholders’ Perspectives," JMIR Human Factors, vol. 8, (3), 2021. Available: https://www.proquest.com/scholarly-journals/machine-learning-based-analysis-encrypted-medical/docview/2577891441/se-2. DOI: https://doi.org/10.2196/21810.

[6] Y. Liu et al, "Verifiable Privacy-Preserving Neural Network on Encrypted Data," Journal of Information Hiding and Privacy Protection, vol. 3, (4), pp. 151-164, 2021. Available: https://www.proquest.com/scholarly-journals/verifiable-privacy-preserving-neural-network-on/docview/2646008984/se-2. DOI: https://doi.org/10.32604/jihpp.2021.026944.

[7] R. Hou et al, "Multi-Party Verifiable Privacy-Preserving Federated k-Means Clustering in Outsourced Environment," Security and Communication Networks, vol. 2021, 2021. Available: https://www.proquest.com/scholarly-journals/multi-party-verifiable-privacy-preserving/docview/2618118126/se-2. DOI: https://doi.org/10.1155/2021/3630312.

[8] J. Shin, S. Choi and C. Yoon-Ho, "Is Homomorphic Encryption-Based Deep Learning Secure Enough?" Sensors, vol. 21, (23), pp. 7806, 2021. Available: https://www.proquest.com/scholarly-journals/is-homomorphic-encryption-based-deep-learning/docview/2608145995/se-2. DOI: https://doi.org/10.3390/s21237806.

[9] X. Sun et al, "A Privacy-Preserving Reinforcement Learning Approach for Dynamic Treatment Regimes on Health Data," Wireless Communications & Mobile Computing (Online), vol. 2021, 2021. Available: https://www.proquest.com/scholarly-journals/privacy-preserving-reinforcement-learning/docview/2606664425/se-2. DOI: https://doi.org/10.1155/2021/8952219.

[10] J. Liu et al, "Secure KNN Classification Scheme Based on Homomorphic Encryption for Cyberspace," Security and Communication Networks, vol. 2021, 2021. Available: https://www.proquest.com/scholarly-journals/secure-knn-classification-scheme-based-on/docview/2597344181/se-2. DOI: https://doi.org/10.1155/2021/8759922.

[11] Z. Chen et al, "Bibliometrics of Machine Learning Research Using Homomorphic Encryption," Mathematics, vol. 9, (21), pp. 2792, 2021. Available: https://www.proquest.com/scholarly-journals/bibliometrics-machine-learning-research-using/docview/2596046878/se-2. DOI: https://doi.org/10.3390/math9212792.

[12] A. Vizitiu et al, "Framework for Privacy-Preserving Wearable Health Data Analysis: Proof-of-Concept Study for Atrial Fibrillation Detection," Applied Sciences, vol. 11, (19), pp. 9049, 2021. Available: https://www.proquest.com/scholarly-journals/framework-privacy-preserving-wearable-health-data/docview/2580962714/se-2. DOI: https://doi.org/10.3390/app11199049.

[13] M. S. Mikail et al, "Homomorphic Encryption Based Privacy-Preservation for IoMT," Applied Sciences, vol. 11, (18), pp. 8757, 2021. Available: https://www.proquest.com/scholarly-journals/homomorphic-encryption-based-privacy-preservation/docview/2576378470/se-2. DOI: https://doi.org/10.3390/app11188757.

[14] Q. Lou, "Efficient Private Deep Learning." Order No. 28716959, Indiana University, United States -- Indiana, 2021.

[15] K. Edemacu, "Multi-Party Privacy-Preserving Logistic Regression with Poor Quality Data Filtering for IoT Contributors," Electronics, vol. 10, (17), pp. 2049, 2021. Available: https://www.proquest.com/scholarly-journals/multi-party-privacy-preserving-logistic/docview/2570775454/se-2. DOI: https://doi.org/10.3390/electronics10172049.

[16] A. B. Popescu et al, "Privacy Preserving Classification of EEG Data Using Machine Learning and Homomorphic Encryption," Applied Sciences, vol. 11, (16), pp. 7360, 2021. Available: https://www.proquest.com/scholarly-journals/privacy-preserving-classification-eeg-data-using/docview/2564633685/se-2. DOI: https://doi.org/10.3390/app11167360.

[17] M. Alkhelaiwi et al, "An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification," Remote Sensing, vol. 13, (11), pp. 2221, 2021. Available: https://www.proquest.com/scholarly-journals/efficient-approach-based-on-privacy-preserving/docview/2539968255/se-2. DOI: https://doi.org/10.3390/rs13112221.

[18] Z. Tan et al, "Distributed Outsourced Privacy-Preserving Gradient Descent Methods among Multiple Parties," Security and Communication Networks, vol. 2021, 2021. Available: https://www.proquest.com/scholarly-journals/distributed-outsourced-privacy-preserving/docview/2520675503/se-2. DOI: https://doi.org/10.1155/2021/8876893.

[19] F. Kuang et al, "Multiparty Homomorphic Machine Learning with Data Security and Model Preservation," Mathematical Problems in Engineering, vol. 2021, 2021. Available: https://www.proquest.com/scholarly-journals/multiparty-homomorphic-machine-learning-with-data/docview/2480125564/se-2. DOI: https://doi.org/10.1155/2021/6615839.

[20] X. Jin et al, "Efficient blind face recognition in the cloud," Multimedia Tools Appl, vol. 79, (17-18), pp. 12533-12550, 2020. Available: https://www.proquest.com/scholarly-journals/efficient-blind-face-recognition-cloud/docview/2397280274/se-2. DOI: https://doi.org/10.1007/s11042-019-08280-y.

[21] A. Alharbi, H. Zamzami and E. Samkri, "Survey on Homomorphic Encryption and Address of New Trend," International Journal of Advanced Computer Science and Applications, vol. 11, (7), 2020. Available: https://www.proquest.com/scholarly-journals/survey-on-homomorphic-encryption-address-new/docview/2655153973/se-2. DOI: https://doi.org/10.14569/IJACSA.2020.0110774.

[22] Anonymous "Privacy-Preserving K-Nearest Neighbors Training over Blockchain-Based Encrypted Health Data," Electronics, vol. 9, (12), pp. 2096, 2020. Available: https://www.proquest.com/scholarly-journals/privacy-preserving-k-nearest-neighbors-training/docview/2469886806/se-2. DOI: https://doi.org/10.3390/electronics9122096.

[23] L. Cheng, L. Yang and J. Ma, "A Secure and Verifiable Outsourcing Scheme for Assisting Mobile Device Training Machine Learning Model," Wireless Communications & Mobile Computing (Online), vol. 2020, 2020. Available: https://www.proquest.com/scholarly-journals/secure-verifiable-outsourcing-scheme-assisting/docview/2465233914/se-2. DOI: https://doi.org/10.1155/2020/8825623.

[24] M. Y. Hong, J. S. Yoo and J. W. Yoon, "Homomorphic Model Selection for Data Analysis in an Encrypted Domain," Applied Sciences, vol. 10, (18), pp. 6174, 2020. Available: https://www.proquest.com/scholarly-journals/homomorphic-model-selection-data-analysis/docview/2441101493/se-2. DOI: https://doi.org/10.3390/app10186174.

[25] S. Carpov et al, "Privacy-preserving semi-parallel logistic regression training with fully homomorphic encryption," BMC Medical Genomics, Suppl.7, vol. 13, pp. 1-10, 2020. Available: https://www.proquest.com/scholarly-journals/privacy-preserving-semi-parallel-logistic/docview/2435109810/se-2. DOI: https://doi.org/10.1186/s12920-020-0723-0.

[26] J. Andrew, S. M. Shaun and B. Mohit, "A Comprehensive Analysis of Privacy-preserving Techniques in Deep learning based Disease Prediction Systems," Journal of Physics: Conference Series, vol. 1362, (1), 2019. Available: https://www.proquest.com/scholarly-journals/comprehensive-analysis-privacy-preserving/docview/2568470021/se-2. DOI: https://doi.org/10.1088/1742-6596/1362/1/012070.

[27] A. Liu et al, "Confidential State Verification for the Delegated Cloud Jobs with Confidential Audit Log," EAI Endorsed Transactions on Security and Safety, vol. 6, (20), 2019. Available: https://www.proquest.com/scholarly-journals/confidential-state-verification-delegated-cloud/docview/2342353633/se-2. DOI: https://doi.org/10.4108/eai.13-7-2018.162290.

[28] T. Lakum and B. Thirumala Rao, "A Key-Ordered Decisional Learning Parity with Noise (DLPN) Scheme for Public Key Encryption Scheme in Cloud Computing," International Journal of Advanced Computer Science and Applications, vol. 10, (11), 2019. Available: https://www.proquest.com/scholarly-journals/key-ordered-decisional-learning-parity-with-noise/docview/2655163325/se-2. DOI: https://doi.org/10.14569/IJACSA.2019.0101121.

[29] F. Tang et al, "Privacy-Preserving Distributed Deep Learning via Homomorphic Re-Encryption," Electronics, vol. 8, (4), pp. 411, 2019. Available: https://www.proquest.com/scholarly-journals/privacy-preserving-distributed-deep-learning-via/docview/2548382292/se-2. DOI: https://doi.org/10.3390/electronics8040411.

[30] M. Salem and S. Taheri, "Utilizing Transfer Learning and Homomorphic Encryption in a Privacy Preserving and Secure Biometric Recognition System," Computers, vol. 8, (1), pp. 3, 2019. Available: https://www.proquest.com/scholarly-journals/utilizing-transfer-learning-homomorphic/docview/2548363513/se-2. DOI: https://doi.org/10.3390/computers8010003.

[31] Preyaa Atri, "Unlocking Data Potential: The GCS XML CSV Transformer for Enhanced Accessibility in Google Cloud", International Journal of Science and Research (IJSR), Volume 8 Issue 10, October 2019, pp. 1870-1871, https://www.ijsr.net/getabstract.php?paperid=SR24608145221

[32] Preyaa Atri. (2021). Automated Object Deletion in Google Cloud Storage: Introducing the Clean-up-gcs-bucket Library. European Journal of Advances in Engineering and Technology, 8(7), 79–83. https://doi.org/10.5281/zenodo.11408114

[33] Chanthati, Sasibhushan Roa. (2021). A segmented approach to encouragement of entrepreneurship using data science. World Journal of Advanced Engineering Technology and Science. https://doi.org/10.30574/wjaets.2024.12.2.0330.

[34] Ayyalasomayajula, M. M. T., Chintala, S., & Sailaja, A. (2019). A Cost-Effective Analysis of Machine Learning Workloads in Public Clouds: Is AutoML Always Worth Using? International Journal of Computer Science Trends and Technology (IJCST), 7(5), 107–115.

[35] Chintala, S. ., & Ayyalasomayajula, M. M. T. . (2019). Optimizing Predictive Accuracy With Gradient Boosted Trees In Financial Forecasting. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 10(3), 1710–1721. https://doi.org/10.61841/turcomat.v10i3.14707

[36] Ayyalasomayajula, M., & Chintala, S. (2020). Fast Parallelizable Cassava Plant Disease Detection using Ensemble Learning with Fine Tuned AmoebaNet and ResNeXt-101. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 11(3), 3013–3023.

[37] Vishwanath Gojanur , Aparna Bhat, “Wireless Personal Health Monitoring System”, IJETCAS:International Journal of Emerging Technologies in Computational and Applied Sciences,eISSN: 2279-0055,pISSN: 2279-0047, 2014.

[38] Aparna Bhat, “Comparison of Clustering Algorithms and Clustering Protocols in Heterogeneous Wireless Sensor Networks: A Survey,” 2014 INTERNATIONAL JOURNAL OF SCIENTIFIC PROGRESS AND RESEARCH (IJSPR)-ISSN : 2349-4689 Volume 04- NO.1, 2014.

[39] Aparna K Bhat, Rajeshwari Hegde, 2014. “Comprehensive Analysis Of Acoustic Echo Cancellation Algorithms On DSP Processor”, International Journal of Advance Computational Engineering and Networking (IJACEN), volume 2, Issue 9, pp.6-11.

Keywords:

Privacy-Preserving Machine Learning, Homomorphic Encryption, Security, Scalability, Cloud Computing.