Document Type

Conference Paper

Publication Date

2025

DOI

10.24963/ijcai.2025/1156

Publication Title

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence

Pages

10409-10417

Conference Name

Thirty-Fourth International Joint Conference on Artificial Intelligence, August 16-22, 2025, Montreal, QC, Canada

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.

Rights

© 2025 International Joint Conferences on Artificial Intelligence Organization.

All Rights Reserved. Included with the kind written permission of the publisher and the authors.

Original Publication Citation

Cheng, S., Li, Z., Meng, S., Ren, M., Xu, H., Hao, S., Yue, C., & Zhang, F. (2025). Understanding PII leakage in large language models: A systematic survey. In James Kwok (Ed.), Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (pp. 10409-10417). International Joint Conferences on Artificial Intelligence. https://doi.org/10.24963/ijcai.2025/1156

ORCID

0000-0001-7483-5252 (Hao)

Download

Share

COinS