Trustworthy AI: Securing Sensitive Data in Large Language Models
Open accessThe DOI matches its Crossref record; 48 of the 48 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421 · cited 1×
“By classifying behavior into normal or abnormal categories, SVMs can detect deviations like abnormal access patterns or excessive requests for sensitive information [128].”
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., & Liu, P. J. (2019) · arXiv · doi:10.48550/arxiv.1910.10683 · Cited by 10,929
An integrative model of organizational trust
Mayer, R. C., Davis, J. H., & Schoorman, F. D. (1995) · The Academy of Management Review · doi:10.2307/258792 · Cited by 10,736
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · doi:10.48550/arxiv.2001.08361 · Cited by 9,550 · cited 1×
“Only recently have new computational resources and optimization techniques enabled the empirical exploration of scaling up LLMs in a way that consistently improves their performance across tasks [50].”
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816 · cited 1×
“Tools like OpenAI GPT models or BART (Bidirectional and Auto-Regressive Trans-formers) are commonly used for summarizing text, which helps maintain the utility of the information without revealing sensitive content [134].”
k-ANONYMITY: A MODEL FOR PROTECTING PRIVACY
SWEENEY, L. (2002) · International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems · doi:10.1142/s0218488502001648 · Cited by 8,571 · cited 2×
“…solutions to achieve the above include mechanisms for strict data curation and consents that forbid training on unauthorized sensitive information [27,28], ways to embed user trust levels and access controls into the LLM systems, and ways to enable dynamic management of the disclosure of…”
On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? 🦜
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445922 · Cited by 6,988 · cited 3×
“It gives very little insight into whether one can predict or control what the model may reveal [20].”
XLNet: Generalized Autoregressive Pretraining for Language Understanding
Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1906.08237 · Cited by 6,687
Cited by
Chow, J. C. L., & Li, K. (2025) · Information · doi:10.3390/info16070549 · Cited by 84
GDPR and Large Language Models: Technical and Legal Obstacles
Feretzakis, G., Vagena, E., Kalodanis, K., Peristera, P., Kalles, D., & Anastasiou, A. (2025) · Future Internet · doi:10.3390/fi17040151 · Cited by 38
Self-citationGalli, C., Gavrilova, A. V., & Calciolari, E. (2025) · Information · doi:10.3390/info16050378 · Cited by 36
Metadata
- Authors
- Feretzakis, G., & Verykios, V. S.
- Venue
- AI
- Publisher
- MDPI AG
- Published
- 2024-12-06
- Volume
- 5
- Issue
- 4
- Pages
- 2773-2800
- ISSN
- 2673-2688 (ISSN-L)
- OpenAlex
- W4405107520
- Cited by
- 83
- References
- 48
- FWCI
- 60.93
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Trustworthy AI: Securing Sensitive Data in Large Language Models. https://app.cochat.ai/papers/10.3390/ai5040134
- The paper
- Feretzakis, G., & Verykios, V. S. (2024). Trustworthy AI: Securing Sensitive Data in Large Language Models. AI. https://doi.org/10.3390/ai5040134
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.