Preprint · 2023 · Open access

PrivateLoRA For Efficient Privacy Preserving LLM

Yiming Wang, Lin Yu, Xiaodong Zeng, Guannan Zhang

arXiv (Cornell University) · Published 23 November 2023 · DOI 10.48550/arxiv.2311.14030

Open PDFView at the publisherCite this paper

In brief

“PrivateLoRA For Efficient Privacy Preserving LLM” is a 2023 preprint by Yiming Wang and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 53 citations as of 19 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
53
Most cited in
2025 (21)
References
33
Authors
4

Abstract

End users face a choice between privacy and efficiency in current Large Language Model (LLM) service paradigms. In cloud-based paradigms, users are forced to compromise data locality for generation quality and processing speed. Conversely, edge device paradigms maintain data locality but fail to deliver satisfactory performance. In this work, we propose a novel LLM service paradigm that distributes privacy-sensitive computation on edge devices and shared computation in the cloud. Only activations are transmitted between the central cloud and edge devices to ensure data locality. Our core innovation, PrivateLoRA, addresses the challenging communication overhead by exploiting the low rank of residual activations, achieving over 95% communication reduction. Consequently, PrivateLoRA effectively maintains data locality and is extremely resource efficient. Under standard 5G networks, PrivateLoRA achieves throughput over 300% of device-only solutions for 7B models and over 80% of an A100 GPU for 33B models. PrivateLoRA also provides tuning performance comparable to LoRA for advanced personalization. Our approach democratizes access to state-of-the-art generative AI for edge devices, paving the way for more tailored LLM experiences for the general public. To our knowledge, our proposed framework is the first efficient and privacy-preserving LLM solution in the literature.

Cite this paper

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

APA 7

Wang, Y., Yu, L., Zeng, X., & Zhang, G. (2023). PrivateLoRA For Efficient Privacy Preserving LLM. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.14030

MLA 9

Wang, Yiming, et al. “PrivateLoRA For Efficient Privacy Preserving LLM.” arXiv (Cornell University), 2023. https://doi.org/10.48550/arxiv.2311.14030.

Chicago

Wang, Yiming, Lin Yu, Xiaodong Zeng, and Guannan Zhang. 2023. “PrivateLoRA For Efficient Privacy Preserving LLM.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.14030.

Harvard

Wang, Y. et al. (2023) ‘PrivateLoRA For Efficient Privacy Preserving LLM’, arXiv (Cornell University). doi:10.48550/arxiv.2311.14030.

IEEE

Y. Wang, L. Yu, X. Zeng, and G. Zhang, “PrivateLoRA For Efficient Privacy Preserving LLM,” arXiv (Cornell University), 2023, doi: 10.48550/arxiv.2311.14030.

BibTeX

@misc{wang2023privatelora,
  title     = {{PrivateLoRA For Efficient Privacy Preserving LLM}},
  author    = {Wang, Yiming and Yu, Lin and Zeng, Xiaodong and Zhang, Guannan},
  howpublished = {arXiv (Cornell University)},
  year      = {2023},
  doi       = {10.48550/arxiv.2311.14030},
  url       = {https://doi.org/10.48550/arxiv.2311.14030}
}

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

Citations by year

YearCitationsShare of the best year
20241313
20252121
20261919

Topic and keywords

Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing

  • edge computing
  • data locality
  • communication efficiency
  • residual activation
  • cloud-edge collaboration
  • LLM personalization
  • LoRa
  • 5G

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?

Wang, Y., Yu, L., Zeng, X., & Zhang, G. (2023). PrivateLoRA For Efficient Privacy Preserving LLM. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2311.14030

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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yiming Wang, Lin Yu, Xiaodong Zeng, Guannan Zhang.

What is the DOI of this paper?

10.48550/arxiv.2311.14030, permanently at https://doi.org/10.48550/arxiv.2311.14030. 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.