Homomorphic encryption–enabled AI processing for IoT security
Mayuri H. Molawademhmolawade@bvucoep.edu.inDepartment of Computer EngineeringCollege of EngineeringBharati Vidyapeeth (Deemed to be University)Pune, Maharashtra, 411043, IndiaView full profile → , *Dhanashree PisalCorresponding authordhanashree.patil89@gmail.comDepartment of Computer ApplicationsIndira College of Engineering & ManagementPune, Maharashtra, 410506, IndiaView full profile → , Prasad M. Patareprasadpatare@gmail.comDepartment of Mechanical EngineeringSanjivani College of EngineeringSavitribai Phule Pune UniversityKopargaon, Ahilyanagar, Maharashtra, 423603, IndiaView full profile → , Sandhya Onkar Ahiresandhyaahire@gmail.comDepartment of Electronics Engineering (VLSI Design & Technology)AISSMS College of EngineeringPune, Maharashtra, 411001, IndiaView full profile → , Sourabh Guhasourabh.guha@rungta.orgDepartment of Computer Science and EngineeringRungta College of Engineering and TechnologyRungta International Skills UniversityBhilai, Chhattisgarh, 490024, IndiaView full profile → , Shubhi Goyalshubhi.mathematics@quantumeducation.inQuantum University Research CenterQuantum UniversityRoorkee, Uttarakhand, 247667, India0009-0001-1684-7324View full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Apr 2026
- Published Online:
- 31 Oct 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JDMSC-3021
- Pages:
- 3937–3949
Abstract
The growth of the Internet of Things (IoT) networks brings with it a number of issues when it comes to safeguarding sensitive data in the context of Artificial Intelligence (AI) based data processing. This paper presents a homomorphic encryption based AI system that can be used to provide privacy-preserving IoT analytics in an integrated sensing, edge computing and cloud intelligence architecture. The framework proposed is based on Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) models, which are also equipped with encrypted inference mechanisms, allowing for the secure analytical performance of operations without revealing the plaintext sensor information. Ciphertext packing, adaptive precision reduction, model pruning, encrypted batch inference and parallel processing are discussed as approaches to address computational optimization. The reported comparative evaluation shows that the proposed encrypted AI framework has an accuracy of 96.2%, precision of 95.4%, recall of 94.7%, and F1 score of 95.0% while conventional AI processing has an accuracy of 97.6%, precision of 96.8%, recall of 96.1%, and F1 score of 96.4%. Compared to the reported data privacy level, the improvement is from 72.5% to 99.1% (a gain of 26.6 percentage points) with only 1.4 percentage point drop in the classification accuracy. These results show that the reported privacy measure and the predictive performance have a good trade-off. The framework could serve as a basis for privacy-preserving intelligent analytics in applications such as healthcare, smart cities and industrial IoT.
Keywords
Subject Classifications
References
[1] A. Albakri, R. Alshahrani, F. Alharbi, and S. B. Ahamed, “Fully homomorphic encryption with optimal key generation secure group communication in Internet of Things environment,” Applied Sciences, vol. 13, no. 10, Art. no. 6055 (2023), doi: 10.3390/app13106055.
[2] R. Raj, Y. Kurt Peker, and Z. D. Mutlu, “Blockchain and homomorphic encryption for data security and statistical privacy,” Electronics, vol. 13, no. 15, Art. no. 3050 (2024), doi: 10.3390/electronics13153050.
[3] R. Kaur, T. Rodrigues, N. Kadir, and R. Kashef, “A survey on privacy preservation techniques in IoT systems,” Sensors, vol. 25, no. 22, Art. no. 6967 (2025), doi: 10.3390/s25226967.
[4] M. Kumar, M. Sethi, S. Rani, D. K. Sah, S. A. AlQahtani, and M. S. Al-Rakhami, “Secure data aggregation based on end-to-end homomorphic encryption in IoT-based wireless sensor networks,” Sensors, vol. 23, no. 13, Art. no. 6181 (2023), doi: 10.3390/s23136181.
[5] J. L. López Delgado, J. A. Álvarez Bermejo, and J. A. López Ramos, “Homomorphic asymmetric encryption applied to the analysis of IoT communications,” Sensors, vol. 22, no. 20, Art. no. 8022v2022), doi: 10.3390/s22208022.
[6] W. Xu, J. Sun, R. Cardell-Oliver, A. Mian, and J. B. Hong, “A privacy-preserving framework using homomorphic encryption for smart metering systems,” Sensors, vol. 23, no. 10, Art. no. 4746 (2023), doi: 10.3390/s23104746.
[7] F. Jerkovic, N. I. Sarkar, and J. Ali, “Smart grid IoT framework for predicting energy consumption using federated learning homomorphic encryption,” Sensors, vol. 25, no. 12, Art. no. 3700 (2025), doi: 10.3390/s25123700.
[8] L. Zhang, C. Li, Q. Hu, J. Lang, S. Huang, L. Hu, J. Leng, Q. Chen, and C. Lv, “Enhancing privacy in large language model with homomorphic encryption and sparse attention,” Applied Sciences, vol. 13, no. 24, Art. no. 13146 (2023), doi: 10.3390/app132413146.
[9] R. C. Poonia, R. Almakki, A. K. J. Saudagar, A. Altameem, and M. Albathan, “An optimization approach for real-time object detection in IoT devices through edge computing and deep learning,” Journal of Information and Optimization Sciences, vol. 45, no. 5, pp. 1465–1475 (2024), doi: 10.47974/JIOS-1768.
[10] S. N. Ajani, P. Khobragade, M. Dhone, B. Ganguly, N. Shelke, and N. Parati, “Advancements in computing: Emerging trends in computational science with next-generation computing,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 7s, pp. 546–559 (2023).
[11] R. C. Poonia, T. Singh, C. K. Rajashri, D. Mondal, and S. M. Patil, “Optimizing communication system security through comprehensive testing and intelligent network configurations,” Journal of Information and Optimization Sciences, vol. 47, no. 5-A, pp. 1709–1717 (2026), doi: 10.47974/JIOS-2261.
[12] J. Kölsch, C. Heinz, A. Ratzke, and C. Grimm, “Simulation-based performance validation of homomorphic encryption algorithms in the Internet of Things,” Future Internet, vol. 11, no. 10, Art. no. 218 (2019), doi: 10.3390/fi11100218.
[13] K. Sharma, S. Bhatt, and M. Khari, “Empirical study on network exploitation tools and vulnerability detection tool,” Journal of Information and Optimization Sciences, vol. 46, no. 5, pp. 1439–1458 (2025), doi: 10.47974/JIOS-1508.
[14] F. Loukil, C. Ghedira-Guegan, K. Boukadi, and A.-N. Benharkat, “Privacy-preserving IoT data aggregation based on blockchain and homomorphic encryption,” Sensors, vol. 21, no. 7, Art. no. 2452 (2021), doi: 10.3390/s21072452.
[15] A. K. Sharma, N. Purohit, S. Joshi, I. U. Lakkewar, and P. Khobragade, “Securing IoT environments: Deep learning-based intrusion detection,” in Deep Learning for Intrusion Detection, F. S. Masoodi and A. Bamhdi, Eds. Wiley (2026), doi: 10.1002/9781394285198.ch12.
[16] J. Wu, Z. Bian, H. Gao, and Y. Wang, “A blockchain-based secure data transaction and privacy preservation scheme in IoT system,” Sensors, vol. 25, no. 15, Art. no. 4854 (2025), doi: 10.3390/s25154854.
[17] S. Umar, J. Nadella, V. Chowdary Dabbara, R. Mannava, and D. Safare, “Leveraging block chain to enhance data integrity and cyber security in supply chain operations,” International Journal of Electrical, Electronics and Computer Systems, vol. 14, no. 1, pp. 260–269 (2025), doi: 10.65521/ijeecs.v14i1.736.
