Document Type

Conference Paper

Publication Date

2026

DOI

10.5220/0014218400004061

Publication Title

Proceedings of the 12th International Conference on Information Systems Security and Privacy -Volume 2 : ICISSP

Volume

2

Pages

141-148

Conference Name

12th International Conference on Information Systems Security and Privacy, March 4-6, 2026, Marbella, Spain

Abstract

Large Language Models (LLMs) are increasingly being adopted in a wide variety of domains, including sensitive domains such as healthcare and finance. However, persistent challenges such as unreliable data sources, privacy breaches, and hallucinated output continue to hinder their usage. We have experimented with several strategies to address these challenges. First, we developed BlockQwen, a blockchain-augmented framework that integrates decentralized trust validation, role-specific access control, and verifiable audit trails into the Qwen 2.5 LLM workflow. Second, we developed PrivAware, a multilayered privacy-enforcement framework, using a fine-tuned Flan-T5 model with self-attention masking, to safeguard data while maintaining high utility. Both systems resulted in significant improvement in mitigating privacy leaks and hallucinations. In this paper, we discuss the challenges that we faced in developing these systems and how these challenges were incrementally overcome. We briefly describe each system, and more importantly, we discuss the lessons learned throughout the development and testing process. It also includes a justification for each of the strategies employed and the benefits gained by such deployments. Finally, we provide guidelines for future development of trustworthy systems using LLMs, with special focus on preventing privacy leaks, minimizing hallucinations, improved authentication and authorization, and immutable audit trails.

Rights

© 2026 by SCITEPRESS -Science and Technology Publications, LDA.

Published under the terms of a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) License.

Original Publication Citation

Kalari, S., Padidela, S., Ashok, V., & Mukkamala, R. (2026). Exploring large language models for trustworthy use: Insights from research and development. In R. D. Pietro, K. Renaud, & Paolo Mori (Eds.), Proceedings of the 12th International Conference on Information Systems Security and Privacy - Volume 2 : ICISSP (pp. 141-148). SciTePress. https://doi.org/10.5220/0014218400004061

ORCID

0009-0003-0927-8252 (Kalari), 0000-0002-4772-1265 (Ashok), 0000-0001-6323-9789 (Mukkamala)

Download

Share

COinS