Abstract
Unexploitable example generation aims to transform personal images into their unexploitable (unlearnable) versions before they are uploaded online, thereby preventing unauthorized exploitation of online personal images. Recently, this task has garnered significant research attention due to its critical relevance to personal data privacy. Yet, despite recent progress, existing methods for this task can still suffer from limited practical applicability, as they can fail to generate examples that are broadly unexploitable across different real-world computer vision tasks. To deal with this problem, in this work, we propose a novel Meta Cross-Task Unexploitable Example Generation (MCT-UEG) framework. At the core of our framework, to optimize the unexploitable example generator for effectively producing broadly unexploitable examples, we design a flat-minima-oriented meta training and testing scheme. Extensive experiments show the efficacy of our framework.
Abstract (translated)
不可利用示例生成旨在将个人图像转换为其不可利用（无法学习）的版本，然后再上传到网上，从而防止未经授权的人滥用在线个人图片。由于这项任务与个人数据隐私密切相关，它最近受到了大量研究的关注。然而，尽管近年来取得了进展，现有方法在实际应用中的效果仍然有限，因为它们生成的例子可能不能广泛地抵御不同现实世界计算机视觉任务的利用。为了解决这个问题，在本工作中，我们提出了一种新颖的元跨任务不可利用示例生成（MCT-UEG）框架。我们的框架的核心在于设计了一个面向平坦极小值的元训练和测试方案，以优化不可利用示例生成器，使其能够有效地产生广泛不可利用的例子。广泛的实验展示了我们框架的有效性。
URL
https://arxiv.org/abs/2512.13416
