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.
Topics & Concepts
Personally identifiable informationComputer scienceMemorizationLanguage modelPersonal information managementInternet privacyArtificial intelligenceComputer securityInformation systemPsychologyCognitive psychologyEngineeringManagement information systemsElectrical engineeringPrivacy-Preserving Technologies in Data