{"type":"ScholarlyArticle","title":"Understanding PII Leakage in Large Language Models: A Systematic Survey","authors":[{"name":"Shuai Cheng","slug":"shuai-cheng","given":"Shuai","family":"Cheng","affiliation":""},{"name":"Zhao Li","slug":"zhao-li","given":"Zhao","family":"Li","affiliation":""},{"name":"Shu Meng","slug":"shu-meng","given":"Shu","family":"Meng","affiliation":""},{"name":"Mengxia Ren","slug":"mengxia-ren","given":"Mengxia","family":"Ren","affiliation":""},{"name":"Haitao Xu","slug":"haitao-xu","given":"Haitao","family":"Xu","affiliation":""},{"name":"Shuai Hao","slug":"shuai-hao","given":"Shuai","family":"Hao","affiliation":""},{"name":"Chuan Yue","slug":"chuan-yue","given":"Chuan","family":"Yue","affiliation":""},{"name":"Fan Zhang","slug":"fan-zhang","given":"Fan","family":"Zhang","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/1156","url":"https://ijcai.org/proceedings/2025/1156","pdf":"https://ijcai.org/proceedings/2025/1156.pdf","markdown":"https://ijcai.org/proceedings/2025/1156.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/1156","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Survey Track","track":"Survey Track","number":1156,"pages":{"first":10409,"last":10417},"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"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}