Conference paper · 2025 · Open access
The Application of Membership Inference in Privacy Auditing of Large Language Models Based on Fine-Tuning Method
International Conference on Generative Artificial Intelligence and Information Security (GAIIS), 473–479 · Published 21 February 2025 · DOI 10.1145/3728725.3728799
In brief
“The Application of Membership Inference in Privacy Auditing of Large Language Models Based on Fine-Tuning Method” is a 2025 conference paper by Chengjiang Wen and 2 co-authors, published in International Conference on Generative Artificial Intelligence and Information Security (GAIIS). OpenAlex counts 1 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at International Conference on Generative Artificial Intelligence and Information Security (GAIIS).
- Citations
- 1
- Most cited in
- 2026 (1)
- Field-weighted impact
- 0.21
- References
- 24
- Authors
- 3
Abstract
Thanks to the large datasets collected from the internet, large language models (LLMs) have made significant progress across various fields, with widespread applications in digital employees, intelligent customer service, and smart decision-making. However, during the training process, models may memorize sensitive private data, posing risks to data security and privacy protection. Member Inference Attacks (MIA) aim to determine whether a specific record was used in the training of the target model. This approach is crucial for detecting privacy risks in models and has seen substantial progress in both traditional and fine-tuned models. However, this remains an unresolved issue for large language models (LLMs). Recent studies indicate that under proper experimental setups, the AUC-ROC of existing methods approaches 0.5 (random guessing). Subsequently, some research has shifted MIA to dataset inference, achieving promising results in this area. Our study shows that when fine-tuning a target model with aggregated samples, it is possible to distinguish whether these samples were used in training the target model by observing the initial loss returned by the model. Based on this observation, we propose a fine-tuning-based member inference method for large language models. To validate the effectiveness of our method, we conducted extensive experiments on three mainstream models and seven datasets. The results indicate that member inference attacks with aggregated samples can achieve acceptable outcomes.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Wen, C., Yue, Y., & Wang, Z. (2025). The Application of Membership Inference in Privacy Auditing of Large Language Models Based on Fine-Tuning Method. International Conference on Generative Artificial Intelligence and Information Security (GAIIS), 473–479. https://doi.org/10.1145/3728725.3728799
MLA 9
Wen, Chengjiang, et al. “The Application of Membership Inference in Privacy Auditing of Large Language Models Based on Fine-Tuning Method.” International Conference on Generative Artificial Intelligence and Information Security (GAIIS), 2025, pp. 473–479. https://doi.org/10.1145/3728725.3728799.
Chicago
Wen, Chengjiang, Yang Yue, and Zhixiang Wang. 2025. “The Application of Membership Inference in Privacy Auditing of Large Language Models Based on Fine-Tuning Method.” International Conference on Generative Artificial Intelligence and Information Security (GAIIS): 473–479. https://doi.org/10.1145/3728725.3728799.
Harvard
Wen, C., Yue, Y. and Wang, Z. (2025) ‘The Application of Membership Inference in Privacy Auditing of Large Language Models Based on Fine-Tuning Method’, International Conference on Generative Artificial Intelligence and Information Security (GAIIS), pp. 473–479. doi:10.1145/3728725.3728799.
IEEE
C. Wen, Y. Yue, and Z. Wang, “The Application of Membership Inference in Privacy Auditing of Large Language Models Based on Fine-Tuning Method,” International Conference on Generative Artificial Intelligence and Information Security (GAIIS), pp. 473–479, 2025, doi: 10.1145/3728725.3728799.
BibTeX
@inproceedings{wen2025application,
title = {{The Application of Membership Inference in Privacy Auditing of Large Language Models Based on Fine-Tuning Method}},
author = {Wen, Chengjiang and Yue, Yang and Wang, Zhixiang},
booktitle = {International Conference on Generative Artificial Intelligence and Information Security (GAIIS)},
year = {2025},
pages = {473--479},
doi = {10.1145/3728725.3728799},
url = {https://doi.org/10.1145/3728725.3728799}
}
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
- membership inference attacks
- large language models
- privacy auditing
- fine-tuning
- training data memorization
- initial loss
- data privacy
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?
Wen, C., Yue, Y., & Wang, Z. (2025). The Application of Membership Inference in Privacy Auditing of Large Language Models Based on Fine-Tuning Method. International Conference on Generative Artificial Intelligence and Information Security (GAIIS), 473–479. https://doi.org/10.1145/3728725.3728799
How many times has this paper been cited?
1 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 International Conference on Generative Artificial Intelligence and Information Security (GAIIS): sign in and open the PDF from this page.
Who wrote this paper?
Chengjiang Wen, Yang Yue, Zhixiang Wang.
What is the DOI of this paper?
10.1145/3728725.3728799, permanently at https://doi.org/10.1145/3728725.3728799. 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.