Conference paper · 2026 · Open access
VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy
Findings of the Association for Computational Linguistics: EACL, 587–609 · Published 1 January 2026 · DOI 10.18653/v1/2026.findings-eacl.29
In brief
“VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy” is a 2026 conference paper by Yu Yan Cui and 4 co-authors, published in Findings of the Association for Computational Linguistics: EACL. OpenAlex counts 12 citations as of 19 November 2026, which puts it in the top 8% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Findings of the Association for Computational Linguistics: EACL.
- Citations
- 12
- Most cited in
- 2026 (10)
- Field-weighted impact
- 8.85
- References
- 43
- Authors
- 5
Abstract
Large language models (LLMs) have been widely deployed in Conversational AIs (CAIs), while exposing privacy and security threats.Recent research shows that LLM-based CAIs can be manipulated to extract private information from human users, posing serious security threats.However, the methods proposed in that study rely on a white-box setting that adversaries can directly modify the system prompt.This condition is unlikely to hold in real-world deployments.The limitation raises a critical question: can unprivileged attackers still induce such privacy risks in practical LLM-integrated applications?To address this question, we propose VORTEXPIA, a novel indirect prompt injection attack that induces privacy extraction in LLM-integrated applications under black-box settings.By injecting token-efficient data containing false memories, VORTEXPIA misleads LLMs to actively request private information in batches.Unlike prior methods, VORTEX-PIA allows attackers to flexibly define multiple categories of sensitive data.We evaluate VORTEXPIA on six LLMs, covering both traditional and reasoning LLMs, across four benchmark datasets.The results show that VORTEXPIA significantly outperforms baselines and achieves state-of-the-art (SOTA) performance.It also demonstrates efficient privacy requests, reduced token consumption, and enhanced robustness against defense mechanisms.We further validate VORTEXPIA on multiple realistic open-source LLM-integrated applications, demonstrating its practical effectiveness.Our code is available at https://github. com/cuiyu-ai/VortexPIA.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Cui, Y. Y., Pan, S., Liu, Y., Zhang, H., & Zuo, C. (2026). VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy. Findings of the Association for Computational Linguistics: EACL, 587–609. https://doi.org/10.18653/v1/2026.findings-eacl.29
MLA 9
Cui, Yu Yan, et al. “VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy.” Findings of the Association for Computational Linguistics: EACL, 2026, pp. 587–609. https://doi.org/10.18653/v1/2026.findings-eacl.29.
Chicago
Cui, Yu Yan, Sicheng Pan, Yifei Liu, Haibin Zhang, and Cong Zuo. 2026. “VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy.” Findings of the Association for Computational Linguistics: EACL: 587–609. https://doi.org/10.18653/v1/2026.findings-eacl.29.
Harvard
Cui, Y. Y. et al. (2026) ‘VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy’, Findings of the Association for Computational Linguistics: EACL, pp. 587–609. doi:10.18653/v1/2026.findings-eacl.29.
IEEE
Y. Y. Cui, S. Pan, Y. Liu, H. Zhang, and C. Zuo, “VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy,” Findings of the Association for Computational Linguistics: EACL, pp. 587–609, 2026, doi: 10.18653/v1/2026.findings-eacl.29.
BibTeX
@inproceedings{cui2026vortexpia,
title = {{VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy}},
author = {Cui, Yu Yan and Pan, Sicheng and Liu, Yifei and Zhang, Haibin and Zuo, Cong},
booktitle = {Findings of the Association for Computational Linguistics: EACL},
year = {2026},
pages = {587--609},
doi = {10.18653/v1/2026.findings-eacl.29},
url = {https://doi.org/10.18653/v1/2026.findings-eacl.29}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- large language models
- black-box attacks
- privacy leakage
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?
Cui, Y. Y., Pan, S., Liu, Y., Zhang, H., & Zuo, C. (2026). VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy. Findings of the Association for Computational Linguistics: EACL, 587–609. https://doi.org/10.18653/v1/2026.findings-eacl.29
How many times has this paper been cited?
12 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 Findings of the Association for Computational Linguistics: EACL: sign in and open the PDF from this page.
Who wrote this paper?
Yu Yan Cui, Sicheng Pan, Yifei Liu, Haibin Zhang, Cong Zuo.
What is the DOI of this paper?
10.18653/v1/2026.findings-eacl.29, permanently at https://doi.org/10.18653/v1/2026.findings-eacl.29. 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.