Blind Computation in AI Machine Operation: A Study of Homomorphic Encryption, Secure Multi-Party Computation, and Federated Learning

Authors

  • Ikechukwu Bismark Owunna Department of Mechanical Engineering, University of Benin, Nigeria
  • Imoh Ekanem * Department of Mechanical Engineering, Akwa Ibom State Polytechic, Ikot Osurua, Nigeria
  • Aniekan Essienubong Ikpe Department of Mechanical Engineering, Akwa Ibom State, Polytechnic, Nigeria.

https://doi.org/10.48314/anowa.v1i4.59

Abstract

This study critically examines the emerging field of Blind Computation (BC) in Artificial Intelligence (AI) machine operations, challenging conventional approaches to data privacy and security in artificial intelligence systems. As AI continues to permeate various sectors, from healthcare to finance, the need for robust privacy-preserving techniques has become paramount.  BC  offers a promising solution by enabling AI models to process encrypted data without decryption, thus maintaining data confidentiality throughout the computational pipeline. The study explored conventional techniques in Homomorphic Encryption (HE), Secure Multi-Party Computation (SMPC), and Federated Learning (FL), presenting a comprehensive framework for implementing  BC  in AI systems. We propose novel architectures that significantly enhance data protection without compromising computational efficiency. The analysis revealed that while  BC  techniques offer unprecedented levels of privacy, they also introduce new challenges in terms of computational overhead and model accuracy. Empirical evidence demonstrating the trade-offs between privacy, performance, and precision, and propose innovative strategies to optimize these competing factors. Furthermore, we critically assess the ethical implications of  BC , examining its potential to either mitigate or exacerbate existing biases in AI systems. This study was concluded by outlining a roadmap for future research, emphasizing the need for interdisciplinary collaboration to address the technical, ethical, and regulatory challenges associated with  BC  in AI. The findings obtained have significant implications on the design and deployment of privacy-preserving AI systems across various domains, potentially revolutionizing the way sensitive data is processed in the age of artificial intelligence.   

Keywords:

Blind computation, AI machine operation, homomorphic encryption, secure multi-party computation

References

  1. [1] Salazar-Calderón, L. A., Izquierdo-Reyes, J., & Javier, A. (2025). Proposal of a methodology for mechatronic design from ideation to embodiment design: Application in a masonry robot case study design. IEEE access. https://doi.org/10.1109/ACCESS.2025.3595509
  2. [2] Rivest, R. L., Adleman, L., & Dertouzos, M. L. (1978). On data banks and privacy homomorphisms. Foundations of secure computation, 4(11), 169-180. https://luca-giuzzi.unibs.it/corsi/Support/papers-cryptography/RAD78.pdf
  3. [3] Koren, Y., Gu, X., & Guo, W. (2018). Reconfigurable manufacturing systems: Principles, design, and future trends. Frontiers of mechanical engineering, 13(2), 121–136. https://doi.org/10.1007/s11465-018-0483-0%0A%0A
  4. [4] Pendleton, S. D., Andersen, H., Du, X., Shen, X., Meghjani, M., Eng, Y. H., … & Ang Jr, M. H. (2017). Perception, planning, control, and coordination for autonomous vehicles. Machines, 5(1), 6. https://doi.org/10.3390/machines5010006
  5. [5] Fitzsimons, J. F. (2017). Private quantum computation: an introduction to blind quantum computing and related protocols. NPJ quantum information, 3(1), 23. https://doi.org/10.1038/s41534-017-0025-3
  6. [6] Diro, A., Reda, H., Chilamkurti, N., Mahmood, A., Zaman, N., & Nam, Y. (2020). Lightweight authenticated-encryption scheme for internet of things based on publish-subscribe communication. Ieee access, 8, 60539–60551. https://doi.org/10.1109/ACCESS.2020.2983117
  7. [7] Cojocaru, A., Colisson, L., Kashefi, E., & Wallden, P. (2021). On the possibility of classical client blind quantum computing. Cryptography, 5(1), 3. https://doi.org/10.3390/cryptography5010003
  8. [8] Oluwafemi, B. (2025). Privacy-preserving computation (homomorphic encryption, MPC). Journal of contemporary educational research, 7, 111–122. https://doi.org/10.5281/zenodo.17282602
  9. [9] Ikpe, A. E., & Ekanem, I. I. (2024). Engineering wired network performance enhancement in a route redistributed simulation based systems. Big data and computing visions, 4(1), 31–48. https://doi.org/10.22105/bdcv.2024.464144.1181
  10. [10] Martins, P., Sousa, L., & Mariano, A. (2017). A survey on fully homomorphic encryption: An engineering perspective. ACM computing surveys (CSUR), 50(6), 1–33. https://dl.acm.org/doi/pdf/10.1145/3124441
  11. [11] Kogos, K. G., Filippova, K. S., & Epishkina, A. V. (2017). Fully homomorphic encryption schemes: The state of the art. 2017 IEEE conference of Russian young researchers in electrical and electronic engineering (EIConRus) (pp. 463-466). IEEE. https://doi.org/10.1109/EIConRus.2017.7910591
  12. [12] Dulek, Y., Schaffner, C., & Speelman, F. (2016). Quantum homomorphic encryption for polynomial-sized circuits. Annual international cryptology conference (pp. 3-32). Berlin, Heidelberg: Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-662-53015-3_1%0A%0A
  13. [13] Achuthan, K., Ramanathan, S., Srinivas, S., & Raman, R. (2024). Advancing cybersecurity and privacy with artificial intelligence: current trends and future research directions. Frontiers in big data, 7, 1497535. https://doi.org/10.3389/fdata.2024.1497535
  14. [14] Akkisetty, P. K. (2025). An overview of AI platforms, frameworks, libraries, and processors. Model optimization methods for efficient and edge AI: Federated learning architectures, frameworks and applications, 43–55. https://doi.org/10.1002/9781394219230.ch3
  15. [15] Sayyad, S., Kulkarni, D., Shikalgar, A., & Mulla, T. A. (2024). An exhaustive survey on privacy preserving machine learning using homomorphic encryption and secure multiparty computation techniques. Journal of computational analysis & applications, 33(5). 636–648. https://eudoxuspress.com/index.php/pub/article/view/590/395
  16. [16] Ikpe, A. E., Ohwoekevwo, J. U., & Ekanem, I. I. (2025). A systematic review on the adoption of IoT and Industry 4.0 in the development of future smart factories to enhance the manufacturing industries. Smart city insights, 2(1), 27–40. https://doi.org/10.22105/sci.v2i1.23
  17. [17] Zhang, Y., Zhao, X., Li, Z., Cheng, G., Yin, J., Zhang, L., & Chen, Z. (2024). Integrating artificial intelligence into operating systems: A survey on techniques, applications, and future directions. https://doi.org/10.48550/arXiv.2407.14567
  18. [18] Foukalas, F. (2025). A survey of artificial neural network computing systems. Cognitive computation, 17(1), 4. https://doi.org/10.1007/s12559-024-10383-0
  19. [19] Venkata, S. S. G. (2025). Secure software development: Integrating encryption protocols from design to deployment. International journal of applied mathematics, 38(2s), 1190–1213. https://doi.org/10.12732/ijam.v38i2s.714
  20. [20] Gnanasudharsan, A., Meena, P., Guru Raghavendra, S., Sreevarshan, S., & Rithika, S. R. (2023). Secure auditing with encrypted trace logs in multi-cloud storage management. 2023 International Conference on Ambient Intelligence, Knowledge Informatics and Industrial Electronics (AIKIIE) (pp. 1-7). IEEE. https://doi.org/10.1109/AIKIIE60097.2023.10389994
  21. [21] Latif, S. A., Wen, F. B. X., Iwendi, C., Wang, L. F., Mohsin, S. M., Han, Z., & Band, S. S. (2022). AI-empowered, blockchain and SDN integrated security architecture for IoT network of cyber physical systems. Computer communications, 181, 274–283. https://doi.org/10.1016/j.comcom.2021.09.029
  22. [22] Ottun, A. R., Marasinghe, R., Elemosho, T., Liyanage, M., Ragab, M., Bagave, P., ... & Flores, H. (2024). The spatial architecture: Design and development experiences from gauging and monitoring the AI inference capabilities of modern applications. 2024 IEEE 44th International Conference on Distributed Computing Systems (ICDCS) (pp. 947-959). IEEE. https://doi.org/10.1109/ICDCS60910.2024.00092
  23. [23] Mollakuqe, E., Parduzi, A., Rexhepi, S., Dimitrova, V., Jakupi, S., Muharremi, R., … & Qarkaxhija, J. (2024). Applications of homomorphic encryption in secure computation. Open research europe, 4, 10–12688. https://doi.org/10.12688/openreseurope.18052.1
  24. [24] Kumar, P. R., & Goel, S. (2025). A secure and efficient encryption system based on adaptive and machine learning for securing data in fog computing. Scientific reports, 15(1), 11654. https://doi.org/10.1038/s41598-025-92245-9
  25. [25] Ekanem, I. I., Ohwoekevwo, J. U., & Ikpe, A. E. (2024). Conjectures of computer vision technology (CVT) on industrial information management systems (IMSs): A futuristic Gaze. Metaheuristic algorithms with applications, 1(1), 20–34. https://doi.org/10.48313/maa.v2i2.43
  26. [26] Khan, F. A., Jamjoom, M., Ahmad, A., & Asif, M. (2022). An analytic study of architecture, security, privacy, query processing, and performance evaluation of database-as-a-service. Transactions on emerging telecommunications technologies, 33(2), e3814. https://doi.org/10.1002/ett.3814
  27. [27] Panda, M. (2016). Performance analysis of encryption algorithms for security. In 2016 International conference on signal processing, communication, power and embedded system (SCOPES) (pp. 278-284). IEEE. https://doi.org/10.1109/SCOPES.2016.7955835
  28. [28] Wang, B. (2025). Application of efficient load test strategies in infrastructure. Journal of computer, signal, and system research, 2(4), 69–75. https://doi.org/10.71222/82kxzb25
  29. [29] Afzal, S., Bokhari, M. U., Luqman, M., & Hanafi, B. (2026). Lightweight CNN-based edge computing with hybrid chaotic encryption for secure and efficient image transmission in IoT networks. Discover computing, 29(1), 65. https://doi.org/10.1007/s10791-026-09942-w%0A%0A
  30. [30] Acar, A., Aksu, H., Uluagac, A. S., & Conti, M. (2018). A survey on homomorphic encryption schemes: Theory and implementation. ACM computing surveys (CSUR), 51(4), 1–35. https://dl.acm.org/doi/pdf/10.1145/3214303
  31. [31] Park, J., Park, S., Park, J. H., Ahn, J. H., Cheon, J. H., Hanrot, G., … & Stehlé, D. (2026). Scaling up Privacy-Preserving ML: A CKKS Implementation of Llama-2-7B. ArXiv preprint arxiv:2601.18511. https://doi.org/10.48550/arXiv.2601.18511
  32. [32] Frimpong, E., Nguyen, K., Budzys, M., Khan, T., & Michalas, A. (2024). Guardml: Efficient privacy-preserving machine learning services through hybrid homomorphic encryption. Proceedings of the 39th ACM/SIGAPP symposium on applied computing (pp. 953-962).. https://doi.org/10.1145/3605098.3635983
  33. [33] Gentry, C. (2009). Fully homomorphic encryption using ideal lattices. In Proceedings of the forty-first annual ACM symposium on theory of computing (pp. 169-178). Association for Computing Machinery. https://doi.org/10.1145/1536414.1536440
  34. [34] Rajpurkar, P., Irvin, J., Bagul, A., Ding, D., Duan, T., Mehta, H., ... & Ng, A. Y. (2017). Mura: Large dataset for abnormality detection in musculoskeletal radiographs. arXiv preprint arXiv:1712.06957.. https://doi.org/10.48550/arXiv.1712.06957
  35. [35] Halevi, G. (2019). Bibliometric studies on gender disparities in science. In Springer handbook of science and technology indicators (pp. 563–580). Springer. https://doi.org/10.1007/978-3-030-02511-3_21
  36. [36] Cheon, J. H., Kim, A., Kim, M., & Song, Y. (2017). Homomorphic encryption for arithmetic of approximate numbers. In International conference on the theory and application of cryptology and information security (pp. 409-437). Cham: Springer International Publishing. https://doi.org/10.1007/978-3-319-70694-8_15
  37. [37] Kim, H., Lee, J. H., & Na, S. H. (2017). Predictor-estimator using multilevel task learning with stack propagation for neural quality estimation. In Proceedings of the second conference on machine translation (pp. 562-568). https://aclanthology.org/W17-4763.pdf
  38. [38] Javed, H., El-Sappagh, S., & Abuhmed, T. (2024). Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust AI applications. Artificial intelligence review, 58(1), 12. https://doi.org/10.1007/s10462-024-11005-9
  39. [39] Ikpe, A. E., Ekanem, I. I., & Owunna, I. B. (2024). Application of brute force algorithm optimization as an industrial hotspot in inventory management and control. Uncertainty discourse and applications, 1(2), 219–236. https://doi.org/10.48313/uda.v1i2.43
  40. [40] Evans, D., Kolesnikov, V., & Rosulek, M. (2018). A pragmatic introduction to secure multi-party computation. Foundations and trends®in privacy and security, 2(2–3), 70–246. https://doi.org/10.1561/3300000019
  41. [41] Ohrimenko, O., Schuster, F., Fournet, C., Mehta, A., Nowozin, S., Vaswani, K., & Costa, M. (2016). Oblivious {Multi-Party} machine learning on trusted processors. In 25th USENIX Security Symposium (USENIX Security 16) (pp. 619-636). https://www.usenix.org/system/files/conference/usenixsecurity16/sec16_paper_ohrimenko.pdf
  42. [42] Alauthman, M., Almomani, A., Aoudi, S., Al-Qerem, A., & Aldweesh, A. (2025). Automated vulnerability discovery generative AI in offensive security. In Examining cybersecurity risks produced by generative AI (pp. 309–328). IGI Global Scientific Publishing. https://doi.org/10.4018/979-8-3373-0832-6.ch013

Downloads

Published

2025-11-15

Issue

Vol. 1 No. 4 (2025): Annals of Optimization With Applications (ANOWA)

Section

Articles

How to Cite

Owunna, I., Ekanem, I., & Ikpe, A. (2025). Blind Computation in AI Machine Operation: A Study of Homomorphic Encryption, Secure Multi-Party Computation, and Federated Learning. Annals of Optimization With Applications, 1(4), 269-287. https://doi.org/10.48314/anowa.v1i4.59

Similar Articles

1-10 of 12

You may also start an advanced similarity search for this article.