Preprint · 2026 · Open access

A Survey on Privacy-Preserving Large LanguageModels (LLMs): Architectures, Techniques, and Use-Cases

Asadullah Tariq, Mohamed Adel Serhani, Ikbal Taleb, Hadeel T. El Kassabi, Alramzana Nujum Navaz, Bouziane Brik

Research Square · Published 20 April 2026 · DOI 10.21203/rs.3.rs-9258244/v1

Open PDFView at the publisherCite this paper

In brief

“A Survey on Privacy-Preserving Large LanguageModels (LLMs): Architectures, Techniques, and Use-Cases” is a 2026 preprint by Asadullah Tariq and 5 co-authors, published in Research Square. OpenAlex counts 0 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at Research Square.

Citations
0
References
158
Authors
6

Abstract

Large Language Models (LLMs) provide powerful capabilities to human language processing, performing very complex tasks ranging from content generation and translation, to reasoning and code generation. This has enabled a wide range of applications in different domains such as finance, education, and healthcare. However, the high reliance on large-scale data and centralized training and inference have created significant concerns related to the data privacy. In fact, processing and generating a large amount of data might leak sensitive information about users. This study provides a comprehensive survey on privacy-preserving LLMs, covering mainly model and architectural designs, risks and attacks, key techniques and their evaluations, and emerging use-cases. We first provide a strong background on privacy-preserving LLMs along with their evolutions and types. We then analyze privacy-preserving LLM deployments and architectures, such as on-device, edge-based, private and cloud-based LLMs. Next, we systematically examine diverse risks and attacks related to the privacy issues. The survey further reviews existing techniques enabling privacy-preserving for LLMs in addition to the existing evaluation methodologies and metrics of privacy -preserving LLMs. The survey also provides a comprehensive taxonomy of privacy-preserving LLMs applications on diverse domains including healthcare, finance and banking, smart home and Internet of things, government services. Finally, we identify still open research questions with their potential future directions.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Tariq, A., Serhani, M. A., Taleb, I., El Kassabi, H. T., Navaz, A. N., & Brik, B. (2026). A Survey on Privacy-Preserving Large LanguageModels (LLMs): Architectures, Techniques, and Use-Cases. Research Square. https://doi.org/10.21203/rs.3.rs-9258244/v1

MLA 9

Tariq, Asadullah, et al. “A Survey on Privacy-Preserving Large LanguageModels (LLMs): Architectures, Techniques, and Use-Cases.” Research Square, 2026. https://doi.org/10.21203/rs.3.rs-9258244/v1.

Chicago

Tariq, Asadullah, Mohamed Adel Serhani, Ikbal Taleb, Hadeel T. El Kassabi, Alramzana Nujum Navaz, and Bouziane Brik. 2026. “A Survey on Privacy-Preserving Large LanguageModels (LLMs): Architectures, Techniques, and Use-Cases.” Research Square. https://doi.org/10.21203/rs.3.rs-9258244/v1.

Harvard

Tariq, A. et al. (2026) ‘A Survey on Privacy-Preserving Large LanguageModels (LLMs): Architectures, Techniques, and Use-Cases’, Research Square. doi:10.21203/rs.3.rs-9258244/v1.

IEEE

A. Tariq, M. A. Serhani, I. Taleb, H. T. El Kassabi, A. N. Navaz, and B. Brik, “A Survey on Privacy-Preserving Large LanguageModels (LLMs): Architectures, Techniques, and Use-Cases,” Research Square, 2026, doi: 10.21203/rs.3.rs-9258244/v1.

BibTeX

@misc{tariq2026survey,
  title     = {{A Survey on Privacy-Preserving Large LanguageModels (LLMs): Architectures, Techniques, and Use-Cases}},
  author    = {Tariq, Asadullah and Serhani, Mohamed Adel and Taleb, Ikbal and El Kassabi, Hadeel T. and Navaz, Alramzana Nujum and Brik, Bouziane},
  howpublished = {Research Square},
  year      = {2026},
  doi       = {10.21203/rs.3.rs-9258244/v1},
  url       = {https://doi.org/10.21203/rs.3.rs-9258244/v1}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data

  • data privacy
  • privacy attacks
  • health care
  • banking and finance
  • public services

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Tariq, A., Serhani, M. A., Taleb, I., El Kassabi, H. T., Navaz, A. N., & Brik, B. (2026). A Survey on Privacy-Preserving Large LanguageModels (LLMs): Architectures, Techniques, and Use-Cases. Research Square. https://doi.org/10.21203/rs.3.rs-9258244/v1

How many times has this paper been cited?

0 times, according to OpenAlex on 19 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Research Square: sign in and open the PDF from this page.

Who wrote this paper?

Asadullah Tariq, Mohamed Adel Serhani, Ikbal Taleb, Hadeel T. El Kassabi, Alramzana Nujum Navaz, Bouziane Brik.

What is the DOI of this paper?

10.21203/rs.3.rs-9258244/v1, permanently at https://doi.org/10.21203/rs.3.rs-9258244/v1. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.