@inproceedings{huang-etal-2022-large,
    title = "Are Large Pre-Trained Language Models Leaking Your Personal Information?",
    author = "Huang, Jie  and
      Shao, Hanyin  and
      Chang, Kevin Chen-Chuan",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.findings-emnlp.148/",
    doi = "10.18653/v1/2022.findings-emnlp.148",
    pages = "2038--2047",
    abstract = "Are Large Pre-Trained Language Models Leaking Your Personal Information? In this paper, we analyze whether Pre-Trained Language Models (PLMs) are prone to leaking personal information. Specifically, we query PLMs for email addresses with contexts of the email address or prompts containing the owner{'}s name. We find that PLMs do leak personal information due to memorization. However, since the models are weak at association, the risk of specific personal information being extracted by attackers is low. We hope this work could help the community to better understand the privacy risk of PLMs and bring new insights to make PLMs safe."
}