Privacy-Preserving Personalization Frameworks for Large Language Models

Authors

  • Swapnil Hemant Thorat University of North Carolina at Charlotte, USA Author

DOI:

https://doi.org/10.32628/CSEIT25112399

Keywords:

Privacy-Preserving AI, Federated Learning, Voice Biometrics Authentication, Differential Privacy, User-Adaptive Systems

Abstract

This article explores innovative approaches to personalizing Large Language Models while maintaining robust privacy protections for users. It examines federated learning architectures, voice biometric authentication, differential privacy techniques, and hierarchical user profiling methods. The investigation delves into developing adaptive frameworks that can securely handle multiple users while preserving individual privacy through advanced encryption and secure processing environments. This article presents a comprehensive analysis of emerging technologies and methodologies that enable personalized AI experiences without compromising user data security. By addressing the critical balance between customization and privacy, this article contributes to the evolving landscape of secure, user-centric AI systems, offering practical solutions for implementing privacy-preserving personalization in modern language models.

Downloads

References

Zhehao Zhang et al., "Personalization of Large Language Models: A Survey," arXiv:2411.00027, 29 Oct. 2024. [Online]. Available: https://arxiv.org/abs/2411.00027

Research Publication, "AI and Personal Privacy: Threats and Protections," SSRN Electronic Journal, vol. 5, no. 5, Jan. 2016. [Online]. Available: https://www.researchgate.net/publication/383278931_AI_and_Personal_Privacy_Threats_and_Protections

Patience Mpofu et al., "A privacy-preserving federated learning architecture implementing data ownership and portability on edge end-points," International Journal of Industrial Engineering and Operations Management, Vol. 5, no. 2, April 2023. [Online]. Available: https://www.researchgate.net/publication/370057348_A_privacy-preserving_federated_learning_architecture_implementing_data_ownership_and_portability_on_edge_end-points

William Villegas-Ch and Joselin García-Ortiz, "Toward a Comprehensive Framework for Ensuring Security and Privacy in Artificial Intelligence," Electronics, vol. 12, no. 18, 7 Sep. 2023. [Online]. Available: https://www.mdpi.com/2079-9292/12/18/3786

Umang H Patel et al., "Biometric Security Systems Enhanced by AI: Exploring Concerns with AI Advancements in Facial Recognition and Other Biometric Systems have Security Implications and Vulnerabilities," International Journal of Innovative Science and Research Technology, vol. 9, no. 6, Jun. 2024. [Online]. Available: https://www.ijisrt.com/assets/upload/files/IJISRT24JUN1510.pdf

Prof. Dipankar Dasgupta, "Adaptive Multi-Factor Authentication (A-MFA) System," The University of Memphis, 30 June 2018. [Online]. Available: https://wiki.uio.no/mn/ifi/AFSecurity/images/f/ff/AFSec20180831-Dasgupta-Memphis.pdf

Jianzhe Zhao et al., "Utility Optimization of Federated Learning with Differential Privacy," Discrete Dynamics in Nature and Society, 8 Oct. 2021. [Online]. Available: https://onlinelibrary.wiley.com/doi/10.1155/2021/3344862

Weijie Liu et al., "Practical and Efficient in-Enclave Verification of Privacy Compliance," Hongbo Chen. [Online]. Available: https://hc50.pages.iu.edu/assets/pdf/In_Enclave_Verification_of_Privacy_Compliance.pdf

MR.S.Subbiah and DR.S.Selva Muthukumaran, "Creating Hierarchical User Profile For Privacy Protection In Personalized Web Search," PARIPEX - Indian Journal of Research, vol. 4, no. 9, Sep. 2015. [Online]. Available: https://www.worldwidejournals.com/paripex/recent_issues_pdf/2015/September/September_2015_1492179630__104.pdf

Youngjung Suh et al., "Context-based User Profile Management for Personalized Services," Citeseerx, June 2005. [Online]. Available: https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=56267a394ff867056bdaf438f1b4b39952ed3a84

Kang Wei et al., "Performance Analysis and Optimization in Privacy-Preserving Federated Learning," ResearchGate, Feb. 2020. [Online]. Available: https://www.researchgate.net/publication/339642424_Performance_Analysis_and_Optimization_in_Privacy-Preserving_Federated_Learning

Geraldine O Mbah, "Data privacy in the era of AI: Navigating regulatory landscapes for global businesses," International Journal of Science and Research Archive, vol. 6, Dec. 2024. [Online]. Available: https://ijsra.net/sites/default/files/IJSRA-2024-2396.pdf

Downloads

Published

08-03-2025

Issue

Section

Research Articles