Trustworthy AI: Securing Sensitive Data in Large Language Models
Large language models (LLMs) have transformed Natural Language Processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises critical concerns about privacy and data security. This paper propo...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/5/4/134 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850042399421628416 |
|---|---|
| author | Georgios Feretzakis Vassilios S. Verykios |
| author_facet | Georgios Feretzakis Vassilios S. Verykios |
| author_sort | Georgios Feretzakis |
| collection | DOAJ |
| description | Large language models (LLMs) have transformed Natural Language Processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises critical concerns about privacy and data security. This paper proposes a comprehensive framework for embedding trust mechanisms into LLMs to dynamically control the disclosure of sensitive information. The framework integrates three core components: User Trust Profiling, Information Sensitivity Detection, and Adaptive Output Control. By leveraging techniques such as Role-Based Access Control (RBAC), Attribute-Based Access Control (ABAC), Named Entity Recognition (NER), contextual analysis, and privacy-preserving methods like differential privacy, the system ensures that sensitive information is disclosed appropriately based on the user’s trust level. By focusing on balancing data utility and privacy, the proposed solution offers a novel approach to securely deploying LLMs in high-risk environments. Future work will focus on testing this framework across various domains to evaluate its effectiveness in managing sensitive data while maintaining system efficiency. |
| format | Article |
| id | doaj-art-b7e937b0289a4f8bbb6ef0dbe5888f80 |
| institution | DOAJ |
| issn | 2673-2688 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AI |
| spelling | doaj-art-b7e937b0289a4f8bbb6ef0dbe5888f802025-08-20T02:55:35ZengMDPI AGAI2673-26882024-12-01542773280010.3390/ai5040134Trustworthy AI: Securing Sensitive Data in Large Language ModelsGeorgios Feretzakis0Vassilios S. Verykios1School of Science and Technology, Hellenic Open University, 26131 Patras, GreeceSchool of Science and Technology, Hellenic Open University, 26131 Patras, GreeceLarge language models (LLMs) have transformed Natural Language Processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises critical concerns about privacy and data security. This paper proposes a comprehensive framework for embedding trust mechanisms into LLMs to dynamically control the disclosure of sensitive information. The framework integrates three core components: User Trust Profiling, Information Sensitivity Detection, and Adaptive Output Control. By leveraging techniques such as Role-Based Access Control (RBAC), Attribute-Based Access Control (ABAC), Named Entity Recognition (NER), contextual analysis, and privacy-preserving methods like differential privacy, the system ensures that sensitive information is disclosed appropriately based on the user’s trust level. By focusing on balancing data utility and privacy, the proposed solution offers a novel approach to securely deploying LLMs in high-risk environments. Future work will focus on testing this framework across various domains to evaluate its effectiveness in managing sensitive data while maintaining system efficiency.https://www.mdpi.com/2673-2688/5/4/134large language modelstrust mechanismssensitive informationrole-based access controlattribute-based access controldata privacy |
| spellingShingle | Georgios Feretzakis Vassilios S. Verykios Trustworthy AI: Securing Sensitive Data in Large Language Models AI large language models trust mechanisms sensitive information role-based access control attribute-based access control data privacy |
| title | Trustworthy AI: Securing Sensitive Data in Large Language Models |
| title_full | Trustworthy AI: Securing Sensitive Data in Large Language Models |
| title_fullStr | Trustworthy AI: Securing Sensitive Data in Large Language Models |
| title_full_unstemmed | Trustworthy AI: Securing Sensitive Data in Large Language Models |
| title_short | Trustworthy AI: Securing Sensitive Data in Large Language Models |
| title_sort | trustworthy ai securing sensitive data in large language models |
| topic | large language models trust mechanisms sensitive information role-based access control attribute-based access control data privacy |
| url | https://www.mdpi.com/2673-2688/5/4/134 |
| work_keys_str_mv | AT georgiosferetzakis trustworthyaisecuringsensitivedatainlargelanguagemodels AT vassiliossverykios trustworthyaisecuringsensitivedatainlargelanguagemodels |