arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.19031cs.CVcs.AI
收藏

面向文档分类的机器遗忘

Machine Unlearning for Document Classification

Computer Vision Center(计算机视觉中心);Universitat Autònoma de Barcelona(巴塞罗那自治大学);College of Computer Science, Nankai University(南开大学计算机学院)

Lei Kang, Mohamed Ali Souibgui, Fei Yang, Lluis Gomez, Ernest Valveny, Dimosthenis Karatzas

AI总结:

本文首次研究文档分类场景下的机器遗忘问题,提出在服务器仅保留少量训练数据的现实条件下实现高效遗忘操作,为文档分析中的隐私保护开辟新方向。

摘要:

文档理解模型近来通过利用大规模用户文档集合展现出卓越性能。然而,由于文档往往包含大量个人数据,其使用可能对用户隐私构成威胁,并削弱人与AI服务之间的信任纽带。为回应这些担忧,倡导“被遗忘权”的立法最近被提出,允许用户请求从计算机系统和神经网络模型中删除私人信息。一种被称为机器遗忘的新方法应运而生,旨在使AI模型遗忘某一特定类别的数据。在我们的研究中,我们探索了面向文档分类问题的机器遗忘,据我们所知,这是该领域的首次研究。具体而言,我们考虑一个现实场景:远程服务器上存放着一个训练良好的模型,且仅拥有训练数据的一小部分。该设置旨在实现高效的遗忘操作。这项工作代表了朝着开发机器遗忘方法以解决文档分析应用中隐私问题迈出的开创性一步。我们的代码已在 \url{https://github.com/leitro/MachineUnlearning-DocClassification} 公开。

英文摘要:

Document understanding models have recently demonstrated remarkable performance by leveraging extensive collections of user documents. However, since documents often contain large amounts of personal data, their usage can pose a threat to user privacy and weaken the bonds of trust between humans and AI services. In response to these concerns, legislation advocating ``the right to be forgotten" has recently been proposed, allowing users to request the removal of private information from computer systems and neural network models. A novel approach, known as machine unlearning, has emerged to make AI models forget about a particular class of data. In our research, we explore machine unlearning for document classification problems, representing, to the best of our knowledge, the first investigation into this area. Specifically, we consider a realistic scenario where a remote server houses a well-trained model and possesses only a small portion of training data. This setup is designed for efficient forgetting manipulation. This work represents a pioneering step towards the development of machine unlearning methods aimed at addressing privacy concerns in document analysis applications. Our code is publicly available at \url{https://github.com/leitro/MachineUnlearning-DocClassification}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑