Preprint · 2026 · Open access
Empirical Evidence of Membership Inference and Training Data Extraction in Open-source Large Language Models
SSRN Electronic Journal · Published 1 January 2026 · DOI 10.2139/ssrn.6944338
In brief
“Empirical Evidence of Membership Inference and Training Data Extraction in Open-source Large Language Models” is a 2026 preprint by Brian Mack, published in SSRN Electronic Journal. OpenAlex counts 0 citations as of 19 November 2026. It is open access: the full text is free to read at SSRN Electronic Journal.
- Citations
- 0
- Authors
- 1
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Mack, B. (2026). Empirical Evidence of Membership Inference and Training Data Extraction in Open-source Large Language Models. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.6944338
MLA 9
Mack, Brian. “Empirical Evidence of Membership Inference and Training Data Extraction in Open-source Large Language Models.” SSRN Electronic Journal, 2026. https://doi.org/10.2139/ssrn.6944338.
Chicago
Mack, Brian. 2026. “Empirical Evidence of Membership Inference and Training Data Extraction in Open-source Large Language Models.” SSRN Electronic Journal. https://doi.org/10.2139/ssrn.6944338.
Harvard
Mack, B. (2026) ‘Empirical Evidence of Membership Inference and Training Data Extraction in Open-source Large Language Models’, SSRN Electronic Journal. doi:10.2139/ssrn.6944338.
IEEE
B. Mack, “Empirical Evidence of Membership Inference and Training Data Extraction in Open-source Large Language Models,” SSRN Electronic Journal, 2026, doi: 10.2139/ssrn.6944338.
BibTeX
@misc{mack2026empirical,
title = {{Empirical Evidence of Membership Inference and Training Data Extraction in Open-source Large Language Models}},
author = {Mack, Brian},
howpublished = {SSRN Electronic Journal},
year = {2026},
doi = {10.2139/ssrn.6944338},
url = {https://doi.org/10.2139/ssrn.6944338}
}
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
- training data extraction
- large language models
- data privacy
- chain-of-thought reasoning
- reinforcement learning from human feedback
- differential privacy
- privacy audit
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?
Mack, B. (2026). Empirical Evidence of Membership Inference and Training Data Extraction in Open-source Large Language Models. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.6944338
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 SSRN Electronic Journal: sign in and open the full text from this page.
Who wrote this paper?
Brian Mack.
What is the DOI of this paper?
10.2139/ssrn.6944338, permanently at https://doi.org/10.2139/ssrn.6944338. 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.