Segue：面向真实世界人脸隐私保护的侧信息引导生成式不可学习样本
Segue: Side-information Guided Generative Unlearnable Examples for Facial Privacy Protection in Real World
AI总结：
针对人脸识别带来的隐私担忧，本文提出 Segue 方法，利用一次训练多次使用的生成模型和侧信息生成不可学习样本，在大幅提升效率（1000倍）的同时保证了跨数据集和模型架构的可迁移性与鲁棒性。
摘要：
人脸识别技术的广泛应用引发了隐私担忧，许多人对其面部数据的收集与使用感到担忧。为解决这些问题，研究人员正积极探索“不可学习样本”的概念，通过在模型训练阶段向数据添加不可感知的扰动，旨在阻止模型学习目标人脸的判别特征。然而，当前方法效率低下，无法同时保证可迁移性和鲁棒性，导致在真实世界中不切实际。为弥补这一缺陷，我们提出了一种名为 Segue：侧信息引导生成式不可学习样本 的新方法。具体而言，我们利用一个一次训练多次使用的模型来生成所需的扰动，而非耗时的基于梯度的方法。为提高可迁移性，我们引入了诸如真实标签和伪标签等侧信息，这些信息在不同场景中本质上是保持一致的。为了增强鲁棒性，训练流程中集成了一个失真层。大量实验表明，所提出的 Segue 比以前的方法快得多（1000倍），并在不同数据集和模型架构之间实现了可迁移的有效性。此外，它能够抵抗 JPEG 压缩、对抗训练以及一些标准数据增强操作。
英文摘要：
The widespread use of face recognition technology has given rise to privacy concerns, as many individuals are worried about the collection and utilization of their facial data. To address these concerns, researchers are actively exploring the concept of ``unlearnable examples", by adding imperceptible perturbation to data in the model training stage, which aims to prevent the model from learning discriminate features of the target face. However, current methods are inefficient and cannot guarantee transferability and robustness at the same time, causing impracticality in the real world. To remedy it, we propose a novel method called Segue: Side-information guided generative unlearnable examples. Specifically, we leverage a once-trained multiple-used model to generate the desired perturbation rather than the time-consuming gradient-based method. To improve transferability, we introduce side information such as true labels and pseudo labels, which are inherently consistent across different scenarios. For robustness enhancement, a distortion layer is integrated into the training pipeline. Extensive experiments demonstrate that the proposed Segue is much faster than previous methods (1000$\times$) and achieves transferable effectiveness across different datasets and model architectures. Furthermore, it can resist JPEG compression, adversarial training, and some standard data augmentations.
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。
