Understanding PII Leakage in Large Language Models: A Systematic Survey

Cheng, Shuai; Li, Zhao; Meng, Shu; Ren, Mengxia; Xu, Haitao; Hao, Shuai; Yue, Chuan; Zhang, Fan

doi:10.24963/ijcai.2025/1156

Understanding PII Leakage in Large Language Models: A Systematic Survey

Shuai Cheng, Zhao Li, Shu Meng, Mengxia Ren, Haitao Xu, Shuai Hao, Chuan Yue, Fan Zhang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Survey Track. Pages 10409-10417.

https://doi.org/10.24963/ijcai.2025/1156

Keywords

AI Ethics, Trust, Fairness: ETF: Safety and robustness
Natural Language Processing: NLP: Language models
AI Ethics, Trust, Fairness: ETF: Ethical, legal and societal issues
Multidisciplinary Topics and Applications: MTA: Security and privacy

Abstract

Large Language Models (LLMs) have demonstrated exceptional success across a variety of tasks, particularly in natural language processing, leading to their growing integration into numerous facets of daily life. However, this widespread deployment has raised substantial privacy concerns, especially regarding personally identifiable information (PII), which can be directly associated with specific individuals. The leakage of such information presents significant real-world privacy threats. In this paper, we conduct a systematic investigation into existing research on PII leakage in LLMs, encompassing commonly utilized PII datasets, evaluation metrics, and current studies on both PII leakage attacks and defensive strategies. Finally, we identify unresolved challenges in the current research landscape and suggest future research directions.

Shuai Cheng, Zhao Li, Shu Meng, Mengxia Ren, Haitao Xu, Shuai Hao, Chuan Yue, and Fan Zhang. 2025. Understanding PII Leakage in Large Language Models: A Systematic Survey. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10409–10417. https://doi.org/10.24963/ijcai.2025/1156

@inproceedings{ijcai2025p1156,
  title     = {Understanding PII Leakage in Large Language Models: A Systematic Survey},
  author    = {Cheng, Shuai and Li, Zhao and Meng, Shu and Ren, Mengxia and Xu, Haitao and Hao, Shuai and Yue, Chuan and Zhang, Fan},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {10409--10417},
  year      = {2025},
  month     = {8},
  note      = {Survey Track},
  doi       = {10.24963/ijcai.2025/1156},
  url       = {https://doi.org/10.24963/ijcai.2025/1156},
}

TY  - CPAPER
TI  - Understanding PII Leakage in Large Language Models: A Systematic Survey
AU  - Cheng, Shuai
AU  - Li, Zhao
AU  - Meng, Shu
AU  - Ren, Mengxia
AU  - Xu, Haitao
AU  - Hao, Shuai
AU  - Yue, Chuan
AU  - Zhang, Fan
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 10409
EP  - 10417
DO  - 10.24963/ijcai.2025/1156
UR  - https://doi.org/10.24963/ijcai.2025/1156
ER  -