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
Trust in Automation: Designing for Appropriate Reliance
Lee, J. D., & See, K. A. (2004) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1518/hfes.46.1.50_30392 · Cited by 6,605
Federated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322 · cited 2×
“This allows for higher privacy and data control with no compromise in the benefits that can be derived from collaborative learning [124]. the proposed framework integrates dynamic trust profiling, information sensitivity detection, and adaptive output control to address the challenge of balancing…”
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Bag of Tricks for Efficient Text Classification
Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · doi:10.18653/v1/e17-2068 · Cited by 4,545
Bag of Tricks for Efficient Text Classification
Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2016) · arXiv · doi:10.48550/arxiv.1607.01759 · Cited by 4,542
Neural Architectures for Named Entity Recognition
Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., & Dyer, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1030 · Cited by 4,401 · cited 4×
“According to this purpose, state-of-the-art NLP approaches such as Named Entity Recognition (NER) [37], text classification [38], and content filtering [31] will be utilized.”
InfluentialThe future of digital health with federated learning
Rieke, N., Hancox, J., Li, W., Milletarì, F., Roth, H. R., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B. A., Maier-Hein, K., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00323-1 · Cited by 4,015 · cited 1×
“Compliance challenges include ensuring data minimization [12], obtaining informed consent for data processing [105], and implementing techniques such as anonymization and pseudonymization to protect personal data [29, 111, 112].”
The Future of Digital Health with Federated Learning
Rieke, N., Hancox, J., Li, W., Milletari, F., Roth, H., Albarqouni, S., Bakas, S., Galtier, M. N., Landman, B., Maier-Hein, K., et al. (2020) · arXiv · doi:10.48550/arxiv.2003.08119 · Cited by 3,495
The EU General Data Protection Regulation (GDPR)
Voigt, P., & von dem Bussche, A. (2017) · doi:10.1007/978-3-319-57959-7 · Cited by 3,001
Trust in Automation: Integrating Empirical Evidence on Factors That Influence Trust
Hoff, K. A., & Bashir, M. (2015) · Human Factors: The Journal of the Human Factors and Ergonomics Society · doi:10.1177/0018720814547570 · Cited by 2,817
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · cited 3×
“This would make AI systems more secure in sensitive areas where protection of data is demanded, such as in health, finance, and legal services [11].”
InfluentialHuman-Centered Artificial Intelligence: Reliable, Safe & Trustworthy
Shneiderman, B. (2020) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2020.1741118 · Cited by 1,743 · cited 2×
“Transparency and explainability [66, 117], fairness and non-discrimination [118], accountability [67, 119], privacy and data governance [60, 120], human-centric design [121].”
How to Fine-Tune BERT for Text Classification?
Sun, C., Qiu, X., Xu, Y., & Huang, X. (2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-32381-3_16 · Cited by 1,534
Privacy in the Digital Age: a Review of Information Privacy Research in Information Systems1
Bélanger, F., & Crossler, R. E. (2011) · MIS Quarterly · doi:10.2307/41409971 · Cited by 1,339 · cited 6×
“Assurance that personal data is protected is essential for trust [58, 60].”
InfluentialOn-line trust: concepts, evolving themes, a model
Corritore, C. L., Kracher, B., & Wiedenbeck, S. (2003) · International Journal of Human-Computer Studies · doi:10.1016/s1071-5819(03)00041-7 · Cited by 1,200 · cited 1×
“Trust in Human-Computer Interaction Trust in human-computer interaction (HCI) is critical for user acceptance and effective use of technology [57, 58].”
Deep reinforcement learning from human preferences
Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S., & Amodei, D. (2017) · arXiv · doi:10.48550/arxiv.1706.03741 · Cited by 1,058 · cited 1×
“…complexities of LLMs [66,117]; ensuring privacy by leveraging methods like differential privacy [14,29] and federated learning [124]; setting up accountabil-15 ity mechanisms to address any harm caused by AI systems [119], and ensuring AI behavior aligns with human values and ethical norms [125].”
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
Liao, Q. V., Gruen, D., & Miller, S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376590 · Cited by 925
Guide to Attribute Based Access Control (ABAC) Definition and Considerations
Hu, V. C., Ferraiolo, D., Kuhn, R., Schnitzer, A., Sandlin, K., Miller, R., & Scarfone, K. (2014) · doi:10.6028/nist.sp.800-162 · Cited by 917 · cited 7×
“For example, if the user’s purpose is to provide a medical diagnosis, the system would disclose more detailed data than for a general research query [36, 54].”
InfluentialEstimating the success of re-identifications in incomplete datasets using generative models
Rocher, L., Hendrickx, J. M., & de Montjoye, Y.-A. (2019) · Nature Communications · doi:10.1038/s41467-019-10933-3 · Cited by 816 · cited 1×
“Compliance challenges include ensuring data minimization [12], obtaining informed consent for data processing [105], and implementing techniques such as anonymization and pseudonymization to protect personal data [29, 111, 112].”
Veale, M., & Zuiderveen Borgesius, F. (2021) · Computer Law Review International · doi:10.9785/cri-2021-220402 · Cited by 805
Trust and Distrust Definitions: One Bite at a Time
Harrison McKnight, D., & Chervany, N. L. (2001) · Lecture Notes in Computer Science · doi:10.1007/3-540-45547-7_3 · Cited by 747 · cited 2×
“Assurance that personal data is protected is essential for trust [58, 60].”
Extracting Training Data from Large Language Models
Carlini, N., Tramer, F., Wallace, E., Jagielski, M., Herbert-Voss, A., Lee, K., Roberts, A., Brown, T., Song, D., Erlingsson, U., et al. (2020) · arXiv · doi:10.48550/arxiv.2012.07805 · Cited by 727 · cited 7×
“Large Language Models can indeed memorize infrequent or unique sequences contained in the training dataset, which later could be verbatim reproduced when a specific prompt is given [9, 15].”
InfluentialRaji, I. D., & Buolamwini, J. (2019) · Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3306618.3314244 · Cited by 651
DARPA's explainable artificial intelligence (XAI) program
Gunning, D. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3308446 · Cited by 546
Machine Learning Models that Remember Too Much
Song, C., Ristenpart, T., & Shmatikov, V. (2017) · Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3133956.3134077 · Cited by 526 · cited 1×
“Attackers can exploit LLMs through model inversion or other methods to extract sensitive data [17] [18].”
Veale, M., & Binns, R. (2017) · Big Data & Society · doi:10.1177/2053951717743530 · Cited by 512
Veale, M., & Binns, R. (2017) · doi:10.31235/osf.io/ustxg · Cited by 512
GLTR: Statistical Detection and Visualization of Generated Text
Gehrmann, S., Strobelt, H., & Rush, A. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/p19-3019 · Cited by 470 · cited 2×
“According to this purpose, state-of-the-art NLP approaches such as Named Entity Recognition (NER) [37], text classification [38], and content filtering [31] will be utilized.”
GLTR: Statistical Detection and Visualization of Generated Text
Gehrmann, S., Strobelt, H., & Rush, A. M. (2019) · arXiv · doi:10.48550/arxiv.1906.04043 · Cited by 460
Lyu, L., Yu, H., Zhao, J., & Yang, Q. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_1 · Cited by 444
A Systematic Review of Re-Identification Attacks on Health Data
El Emam, K., Jonker, E., Arbuckle, L., & Malin, B. (2011) · PLoS ONE · doi:10.1371/journal.pone.0028071 · Cited by 427 · cited 4×
“Automated sanitization may miss context-specific or subtle forms of sensitive information, while manual sanitization of billions of words in datasets becomes practically impossible [28].”
InfluentialThreats to federated learning A survey
Lyu, L., Yu, H., & Yang, Q. (2020) · arXiv · doi:10.48550/arxiv.2003.02133 · Cited by 221 · cited 1×
“General methods of preventing unauthorized disclosure of sensitive information by LLMs include data sanitization, differential privacy, and output filtering [14], [24], [25].”
Cavoukian, A. (2012) · Privacy Protection Measures and Technologies in Business Organizations · doi:10.4018/978-1-61350-501-4.ch007 · Cited by 209 · cited 1×
“Implementing content filtering and DLP methods presents challenges such as balancing security with usability, managing false positives, and ensuring compliance with privacy regulations [97,98].”
Healthcare data breaches: Implications for digital forensic readiness
Chernyshev, M., Zeadally, S., & Baig, Z. (2019) · Journal of Medical Systems · doi:10.1007/s10916-018-1123-2 · Cited by 118 · cited 1×
“Network DLP works by monitoring network traffic to prevent unauthorized data transfers via email or web applications, among other protocols [92].”
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
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.