CURE：面向人脸识别系统的质心引导无监督表示擦除
CURE: Centroid-guided Unsupervised Representation Erasure for Facial Recognition Systems
AI总结：
针对人脸识别中隐私删除需身份标签的难题，提出无监督遗忘框架CURE，无需标签即可移除目标样本，并引入UES指标平衡遗忘与保留，显著优于现有方法。
摘要：
在当前的数字时代，人脸识别系统提供了显著的实用性，并已广泛集成到现代技术基础设施中；然而，其广泛使用也引发了严重的隐私担忧，促使相关法规要求在用户请求时进行数据删除。机器遗忘已成为解决该问题的有力方案，通过从训练模型中选择性移除特定用户数据的影响，同时保持整体模型性能。然而，现有的机器遗忘技术大多依赖于需要身份标签的监督方法，而在隐私受限场景或大规模、嘈杂数据集中，这些标签往往不可用。为解决这一关键缺口，我们提出了CURE（质心引导无监督表示擦除），这是首个无需身份标签即可运行的人脸识别系统无监督遗忘框架，能够有效移除目标样本同时保持整体性能。我们还提出了一种新颖的评估指标——遗忘效率分数（UES），该指标平衡了遗忘与保留稳定性，弥补了当前评估指标的不足。CURE显著优于现有遗忘方法的无监督变体。此外，我们通过将低质量图像指定为遗忘集进行了质量感知的遗忘实验，展示了其实用性和益处，并强调了图像质量在机器遗忘中的作用。
英文摘要：
In the current digital era, facial recognition systems offer significant utility and have been widely integrated into modern technological infrastructures; however, their widespread use has also raised serious privacy concerns, prompting regulations that mandate data removal upon request. Machine unlearning has emerged as a powerful solution to address this issue by selectively removing the influence of specific user data from trained models while preserving overall model performance. However, existing machine unlearning techniques largely depend on supervised techniques requiring identity labels, which are often unavailable in privacy-constrained situations or in large-scale, noisy datasets. To address this critical gap, we introduce CURE (Centroid-guided Unsupervised Representation Erasure), the first unsupervised unlearning framework for facial recognition systems that operates without the use of identity labels, effectively removing targeted samples while preserving overall performance. We also propose a novel metric, the Unlearning Efficiency Score (UES), which balances forgetting and retention stability, addressing shortcomings in the current evaluation metrics. CURE significantly outperforms unsupervised variants of existing unlearning methods. Additionally, we conducted quality-aware unlearning by designating low-quality images as the forget set, demonstrating its usability and benefits, and highlighting the role of image quality in machine unlearning.
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。
