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.
翻译:在本文中,我们分析培训前语言模型(PLM)是否容易泄露个人信息。具体地说,我们查询PLMs的电子邮件地址与电子邮件地址的背景或包含所有者姓名的提示。我们发现,PLMs确实由于记忆化而泄露个人信息。然而,由于这些模型关系薄弱,攻击者提取具体个人信息的风险较低。我们希望这项工作能够帮助社区更好地理解PLMs的隐私风险,并带来新的洞察力,使PLMs安全。