arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.02240cs.CV
收藏

面向机器遗忘基准:在面部识别系统中遗忘个人身份

Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systems

Kyunghee University(庆熙大学);MODULABS;Pohang University of Science and Technology (POSTECH)(浦项科技大学)

Dasol Choi, Dongbin Na

AI总结:

提出面向面部识别系统的机器遗忘基准,针对个人身份遗忘设置,构建MUFAC和MUCAC数据集,评估现有遗忘算法性能并公开资源。

摘要:

机器遗忘是一种关键工具,能使分类模型遗忘训练时使用的特定数据。近年来,多项研究提出了机器遗忘算法,并在多个数据集上评估了其方法。然而,目前大多数机器遗忘算法仅在传统计算机视觉数据集(如CIFAR-10、MNIST和SVHN)上进行评估。此外,以往研究通常在类遗忘设置下评估遗忘方法。大多数先前工作首先训练分类模型,然后通过遗忘实验中选择的图像类别(类别)来评估机器遗忘算法的机器遗忘性能。不幸的是,这些类遗忘设置可能无法推广到现实世界场景。在这项工作中,我们提出了一种机器遗忘设置,旨在遗忘包含个人隐私(身份)的特定实例,同时保持给定模型的原始任务。具体而言,我们提出了两个机器遗忘基准数据集MUFAC和MUCAC,它们对于评估机器遗忘算法的性能和鲁棒性非常有用。在我们的基准数据集中,原始模型执行面部特征识别任务:面部年龄估计(多类分类)和面部属性分类(二类分类),其中类别不依赖于任何单个目标主体(个人身份),这可以是一个现实的设置。此外,我们还报告了最先进的机器遗忘方法在我们提出的基准数据集上的性能。所有数据集、源代码和训练模型均可公开获取,网址为https://github.com/ndb796/MachineUnlearning。

英文摘要:

Machine unlearning is a crucial tool for enabling a classification model to forget specific data that are used in the training time. Recently, various studies have presented machine unlearning algorithms and evaluated their methods on several datasets. However, most of the current machine unlearning algorithms have been evaluated solely on traditional computer vision datasets such as CIFAR-10, MNIST, and SVHN. Furthermore, previous studies generally evaluate the unlearning methods in the class-unlearning setup. Most previous work first trains the classification models and then evaluates the machine unlearning performance of machine unlearning algorithms by forgetting selected image classes (categories) in the experiments. Unfortunately, these class-unlearning settings might not generalize to real-world scenarios. In this work, we propose a machine unlearning setting that aims to unlearn specific instance that contains personal privacy (identity) while maintaining the original task of a given model. Specifically, we propose two machine unlearning benchmark datasets, MUFAC and MUCAC, that are greatly useful to evaluate the performance and robustness of a machine unlearning algorithm. In our benchmark datasets, the original model performs facial feature recognition tasks: face age estimation (multi-class classification) and facial attribute classification (binary class classification), where a class does not depend on any single target subject (personal identity), which can be a realistic setting. Moreover, we also report the performance of the state-of-the-art machine unlearning methods on our proposed benchmark datasets. All the datasets, source codes, and trained models are publicly available at https://github.com/ndb796/MachineUnlearning.

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。

↑