IN THE ENVIRONMENT OF ARTIFICIAL INTELLIGENCE (AI), IOT DATA PROTECTION BASED ON HOMOMORPHIC ENCRYPTING ALGORITHMS

Authors

  • Berdax Abdirazakovich Saparniyazov

    National University of Uzbekistan image/svg+xml

  • Islambek Mirzabaevich Saymanov

    National University of Uzbekistan image/svg+xml

  • Axmet Qidirbayevich Bazarbaev

    Nukus state technical university

  • Nesibeli Userbayevna Shaniyazova

    Nukus state technical university

Keywords: IoT, аrtificial intelligence, homomorphic encryption, Paillier, BFV, CKKS, privacy, cybersecurity, linear regression

Abstract

This paper investigates the preservation of data privacy generated by Internet of Things (IoT) devices during processing within artificial intelligence (AI) environments. To ensure the security of IoT data, homomorphic encryption (HE) algorithms (PHE, SHE, FHE) are analyzed. The mechanisms for executing mathematical operations on encrypted data within AI models (using linear regression as an example) are studied using Paillier, BFV, and CKKS schemes. The models are compared based on accuracy, computational latency, and memory overhead, and the most efficient algorithm is selected.

References

1. Gentry C. A fully homomorphic encryption scheme (Doctoral dissertation, Stanford University). Chapter 4, -P. 95-120. 2009.

2. Paillier P. Public-key cryptosystems based on composite degree residuosity classes. In Advances in Cryptology — EUROCRYPT ’99, -P. 223-238. 1999.

3. Fan J., and Vercauteren, F. (2012). Somewhat Practical Fully Homomorphic Encryption. IACR Cryptol. ePrint Arch., 2012, -P. 144.

4. Cheon J.H., Kim A., Kim M., Song Y. Homomorphic encryption for arithmetic of approximate numbers. In International cryptography (Asiacrypt 2017), pp. 409–437.

5. Olaniyi O.O. A Novel AI-Driven Homomorphic Encryption Framework for Secure Real-Time Telehealth Data Analysis. Asian Journal of Research in Computer Science, 18(11), -P. 1-17. 2025.

6. Ullah S., Li J., et al. Homomorphic Encryption Applications for IoT and Light-Weighted Environments: A Review. IEEE Internet of Things Journal, 12(2), -P. 45-58. 2025.

7. Zokirov S.I., Inomjonov I.T., Nuraliyev S.S. Gomomorfik shifrlash (FHE) usullari va algoritmlari tahlili. Avtomatlashtirish, Elektronika va Sun’iy Intellekt Respublika Konferensiyasi materiallari, 1(1), 2-3 b. 2026.

8. Rivest R.L., Adleman L., Dertouzos M.L. On data banks and privacy homomorphisms. Foundations of secure computation, 4(11), -P. 169-180. 1978.

9. Brakerski Z. Fully homomorphic encryption without modulus switching. In Advances in Cryptology – CRYPTO 2012, -P. 868-886.

10. Halevi S., Shoup V. Algorithms in HElib. In Advances in Cryptology – CRYPTO 2014, -P. 554-571.

11. Kim M., Lauter K. Private AI: Machine learning on encrypted data. IACR Cryptology ePrint Archive, 2015.