Are Large Pre-Trained Language Models Leaking Your Personal Information?
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.
PDF Abstract
Datasets
Introduced in the Paper:
LM Email Address LeakageResults from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
Methods
No methods listed for this paper. Add
relevant methods here
