Preprint · 2024 · Open access

"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction

Shuning Zhang, Lyumanshan Ye, Xin Yi, Jingyu Tang, Bo Shui, Haobin Xing, Pengfei Liu, Hewu Li

arXiv (Cornell University) · Published 19 October 2024 · DOI 10.48550/arxiv.2410.14931

Open PDFView at the publisherCite this paper

In brief

“"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction” is a 2024 preprint by Shuning Zhang and 7 co-authors, published in arXiv (Cornell University). OpenAlex counts 42 citations as of 19 November 2026. It is open access under a CC BY-SA licence: the full text is free to read at arXiv (Cornell University).

Citations
42
Most cited in
2026 (22)
References
76
Authors
8

Abstract

Memories, encompassing past inputs in context window and retrieval-augmented generation (RAG), frequently surface during human-LLM interactions, yet users are often unaware of their presence and the associated privacy risks. To address this, we propose MemoAnalyzer, a system for identifying, visualizing, and managing private information within memories. A semi-structured interview (N=40) revealed that low privacy awareness was the primary challenge, while proactive privacy control emerged as the most common user need. MemoAnalyzer uses a prompt-based method to infer and identify sensitive information from aggregated past inputs, allowing users to easily modify sensitive content. Background color temperature and transparency are mapped to inference confidence and sensitivity, streamlining privacy adjustments. A 5-day evaluation (N=36) comparing MemoAnalyzer with the default GPT setting and a manual modification baseline showed MemoAnalyzer significantly improved privacy awareness and protection without compromising interaction speed. Our study contributes to privacy-conscious LLM design, offering insights into privacy protection for Human-AI interactions.

Cite this paper

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

APA 7

Zhang, S., Ye, L., Yi, X., Tang, J., Shui, B., Xing, H., Liu, P., & Li, H. (2024). "Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.14931

MLA 9

Zhang, Shuning, et al. “"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction.” arXiv (Cornell University), 2024. https://doi.org/10.48550/arxiv.2410.14931.

Chicago

Zhang, Shuning, Lyumanshan Ye, Xin Yi, Jingyu Tang, Bo Shui, Haobin Xing, Pengfei Liu, and Hewu Li. 2024. “"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.14931.

Harvard

Zhang, S. et al. (2024) ‘"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction’, arXiv (Cornell University). doi:10.48550/arxiv.2410.14931.

IEEE

S. Zhang et al., “"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction,” arXiv (Cornell University), 2024, doi: 10.48550/arxiv.2410.14931.

BibTeX

@misc{zhang2024ghost,
  title     = {{"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction}},
  author    = {Zhang, Shuning and Ye, Lyumanshan and Yi, Xin and Tang, Jingyu and Shui, Bo and Xing, Haobin and Liu, Pengfei and Li, Hewu},
  howpublished = {arXiv (Cornell University)},
  year      = {2024},
  doi       = {10.48550/arxiv.2410.14931},
  url       = {https://doi.org/10.48550/arxiv.2410.14931}
}

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

Topic and keywords

Social Sciences › Social Sciences › Sociology and Political Science › Privacy, Security, and Data Protection

  • privacy leakage
  • LLM memory
  • retrieval-augmented generation
  • context window
  • privacy awareness
  • human-AI interaction

Work with this paper

Most-cited papers in Social Sciences

All highly cited Social Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Zhang, S., Ye, L., Yi, X., Tang, J., Shui, B., Xing, H., Liu, P., & Li, H. (2024). "Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interaction. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2410.14931

How many times has this paper been cited?

42 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?

Shuning Zhang, Lyumanshan Ye, Xin Yi, Jingyu Tang, Bo Shui, Haobin Xing, Pengfei Liu, Hewu Li.

What is the DOI of this paper?

10.48550/arxiv.2410.14931, permanently at https://doi.org/10.48550/arxiv.2410.14931. 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.