Are Large Pre-Trained Language Models Leaking Your Personal Information?

Jie Huang, Hanyin Shao, Kevin Chen-Chuan Chang


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.
Anthology ID:
2022.findings-emnlp.148
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2038–2047
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.148
DOI:
10.18653/v1/2022.findings-emnlp.148
Bibkey:
Cite (ACL):
Jie Huang, Hanyin Shao, and Kevin Chen-Chuan Chang. 2022. Are Large Pre-Trained Language Models Leaking Your Personal Information?. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 2038–2047, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Are Large Pre-Trained Language Models Leaking Your Personal Information? (Huang et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2022.findings-emnlp.148.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-2/2022.findings-emnlp.148.mp4