Conference paper · 2025 · Open access
EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling
IEEE International Conference on Acoustics Speech and Signal Processing, 1–5 · Published 12 March 2025 · DOI 10.1109/icassp49660.2025.10888320
In brief
“EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling” is a 2025 conference paper by Zichen Song and 2 co-authors, published in IEEE International Conference on Acoustics Speech and Signal Processing. OpenAlex counts 7 citations as of 19 November 2026, which puts it in the top 4% of works published in 2025 by citations. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 7
- Most cited in
- 2025 (4)
- Field-weighted impact
- 1.45
- References
- 42
- Authors
- 3
Abstract
With the widespread application of large language models (LLM), concerns about the privacy leakage of model training data have increasingly become a focus. Membership Inference Attacks (MIAs) have emerged as a critical tool for evaluating the privacy risks associated with these models. Although existing attack methods, such as LOSS, Reference-based, min-k, and zlib, perform well in certain scenarios, their effectiveness on large pre-trained language models often approaches random guessing, particularly in the context of large-scale datasets and single-epoch training. To address this issue, this paper proposes a novel ensemble attack method that integrates several existing MIAs techniques (LOSS, Reference-based, min-k, zlib) into an XGBoost-based model to enhance overall attack performance (EM-MIAs). Experimental results demonstrate that the ensemble model significantly improves both AUC-ROC and accuracy compared to individual attack methods across various large language models and datasets. This indicates that by combining the strengths of different methods, we can more effectively identify members of the model’s training data, thereby providing a more robust tool for evaluating the privacy risks of LLM. This study offers new directions for further research in the field of LLM privacy protection and underscores the necessity of developing more powerful privacy auditing methods.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Song, Z., Huang, S., & Kang, Z. (2025). EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling. IEEE International Conference on Acoustics Speech and Signal Processing, 1–5. https://doi.org/10.1109/icassp49660.2025.10888320
MLA 9
Song, Zichen, et al. “EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling.” IEEE International Conference on Acoustics Speech and Signal Processing, 2025, pp. 1–5. https://doi.org/10.1109/icassp49660.2025.10888320.
Chicago
Song, Zichen, Sitan Huang, and Zhongfeng Kang. 2025. “EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling.” IEEE International Conference on Acoustics Speech and Signal Processing: 1–5. https://doi.org/10.1109/icassp49660.2025.10888320.
Harvard
Song, Z., Huang, S. and Kang, Z. (2025) ‘EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling’, IEEE International Conference on Acoustics Speech and Signal Processing, pp. 1–5. doi:10.1109/icassp49660.2025.10888320.
IEEE
Z. Song, S. Huang, and Z. Kang, “EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling,” IEEE International Conference on Acoustics Speech and Signal Processing, pp. 1–5, 2025, doi: 10.1109/icassp49660.2025.10888320.
BibTeX
@inproceedings{song2025mias,
title = {{EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling}},
author = {Song, Zichen and Huang, Sitan and Kang, Zhongfeng},
booktitle = {IEEE International Conference on Acoustics Speech and Signal Processing},
year = {2025},
pages = {1--5},
doi = {10.1109/icassp49660.2025.10888320},
url = {https://doi.org/10.1109/icassp49660.2025.10888320}
}
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
- ensemble attacks
- XGBoost
- pre-trained language models
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?
Song, Z., Huang, S., & Kang, Z. (2025). EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling. IEEE International Conference on Acoustics Speech and Signal Processing, 1–5. https://doi.org/10.1109/icassp49660.2025.10888320
How many times has this paper been cited?
7 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 arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Zichen Song, Sitan Huang, Zhongfeng Kang.
What is the DOI of this paper?
10.1109/icassp49660.2025.10888320, permanently at https://doi.org/10.1109/icassp49660.2025.10888320. 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.