arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.11577cs.LGcs.CR
收藏

特征与标签的机器遗忘

Machine Unlearning of Features and Labels

Technische Universität Braunschweig(布伦瑞克工业大学);KASTEL Security Research Labs, Karlsruhe Institute of Technology (KIT)(卡尔斯鲁厄理工学院(KIT)KASTEL安全研究实验室)

Alexander Warnecke, Lukas Pirch, Christian Wressnegger, Konrad Rieck

AI总结:

本文提出首个基于影响函数和闭式参数更新的特征与标签机器遗忘方法,可追溯纠正数据泄露,在强凸损失下具有理论保证,在非凸损失下实验证明有效且显著更快。

摘要:

从机器学习模型中移除信息是一项非平凡的任务,需要部分逆转训练过程。当敏感数据(如信用卡号或密码)意外进入模型并需要在事后删除时,这项任务不可避免。最近,针对机器遗忘提出了不同的概念以解决这一问题。虽然这些方法在移除单个数据点方面有效,但它们无法扩展到需要撤销更大规模特征组和标签组的场景。在本文中,我们提出了首个用于遗忘特征和标签的方法。我们的方法建立在影响函数的概念之上,并通过模型参数的闭式更新实现遗忘。它能够追溯性地调整训练数据对学习模型的影响,从而纠正数据泄露和隐私问题。对于具有强凸损失函数的学习模型,我们的方法提供了具有理论保证的认证遗忘。对于具有非凸损失的模型,我们通过实验表明,遗忘特征和标签是有效的,并且显著快于其他策略。

英文摘要:

Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the model and need to be removed afterwards. Recently, different concepts for machine unlearning have been proposed to address this problem. While these approaches are effective in removing individual data points, they do not scale to scenarios where larger groups of features and labels need to be reverted. In this paper, we propose the first method for unlearning features and labels. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters. It enables to adapt the influence of training data on a learning model retrospectively, thereby correcting data leaks and privacy issues. For learning models with strongly convex loss functions, our method provides certified unlearning with theoretical guarantees. For models with non-convex losses, we empirically show that unlearning features and labels is effective and significantly faster than other strategies.

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。

↑