Journal article · 2024 · Open access
Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy
Journal of Software Engineering and Applications, 17(01), 1–22 · Published 1 January 2024 · DOI 10.4236/jsea.2024.171001
In brief
“Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy” is a 2024 journal article by Tanmay Singh and 3 co-authors, published in Journal of Software Engineering and Applications. OpenAlex counts 53 citations as of 19 November 2026, which puts it in the top 1% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at Journal of Software Engineering and Applications.
- Citations
- 53
- Most cited in
- 2025 (32)
- Field-weighted impact
- 4.42
- References
- 18
- Authors
- 4
Abstract
The proliferation of Large Language Models (LLMs) across various sectors underscored the urgency of addressing potential privacy breaches. Vulnerabilities, such as prompt injection attacks and other adversarial tactics, could make these models inadvertently disclose their training data. Such disclosures could compromise personal identifiable information, posing significant privacy risks. In this paper, we proposed a novel multi-faceted approach called Whispered Tuning to address privacy leaks in large language models (LLMs). We integrated a PII redaction model, differential privacy techniques, and an output filter into the LLM fine-tuning process to enhance confidentiality. Additionally, we introduced novel ideas like the Epsilon Dial for adjustable privacy budgeting for differentiated Training Phases per data handler role. Through empirical validation, including attacks on non-private models, we demonstrated the robustness of our proposed solution SecureNLP in safeguarding privacy without compromising utility. This pioneering methodology significantly fortified LLMs against privacy infringements, enabling responsible adoption across sectors.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Singh, T., Aditya, H., Madisetti, V. K., & Bahga, A. (2024). Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy. Journal of Software Engineering and Applications, 17(01), 1–22. https://doi.org/10.4236/jsea.2024.171001
MLA 9
Singh, Tanmay, et al. “Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy.” Journal of Software Engineering and Applications, vol. 17, no. 01, 2024, pp. 1–22. https://doi.org/10.4236/jsea.2024.171001.
Chicago
Singh, Tanmay, Harshvardhan Aditya, Vijay Krishna Madisetti, and Arshdeep Bahga. 2024. “Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy.” Journal of Software Engineering and Applications 17 (01): 1–22. https://doi.org/10.4236/jsea.2024.171001.
Harvard
Singh, T. et al. (2024) ‘Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy’, Journal of Software Engineering and Applications, 17(01), pp. 1–22. doi:10.4236/jsea.2024.171001.
IEEE
T. Singh, H. Aditya, V. K. Madisetti, and A. Bahga, “Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy,” Journal of Software Engineering and Applications, vol. 17, no. 01, pp. 1–22, 2024, doi: 10.4236/jsea.2024.171001.
BibTeX
@article{singh2024whispered,
title = {{Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy}},
author = {Singh, Tanmay and Aditya, Harshvardhan and Madisetti, Vijay Krishna and Bahga, Arshdeep},
journal = {Journal of Software Engineering and Applications},
year = {2024},
volume = {17},
number = {01},
pages = {1--22},
doi = {10.4236/jsea.2024.171001},
url = {https://doi.org/10.4236/jsea.2024.171001}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 10 | |
| 2025 | 32 | |
| 2026 | 11 |
Its field-weighted citation impact is 4.42: it has been cited 4.42 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- differential privacy
- large language models
- LLM fine-tuning
- data privacy preservation
- prompt injection
- output filtering
- training data leakage
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Singh, T., Aditya, H., Madisetti, V. K., & Bahga, A. (2024). Whispered Tuning: Data Privacy Preservation in Fine-Tuning LLMs through Differential Privacy. Journal of Software Engineering and Applications, 17(01), 1–22. https://doi.org/10.4236/jsea.2024.171001
How many times has this paper been cited?
53 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 Journal of Software Engineering and Applications: sign in and open the PDF from this page.
Who wrote this paper?
Tanmay Singh, Harshvardhan Aditya, Vijay Krishna Madisetti, Arshdeep Bahga.
What is the DOI of this paper?
10.4236/jsea.2024.171001, permanently at https://doi.org/10.4236/jsea.2024.171001. 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.