让个人图像生成难被任何任务利用的版本，保护隐私。
Learning to Generate Cross-Task Unexploitable Examples
- 用元学习优化生成器，使其在多种任务下都难以被利用
- 在多个真实视觉任务上验证，生成样本几乎无法被识别
- 适合关注在线图像隐私保护的研究者和开发者
不可利用样本生成旨在将个人图像转换为难以被学习的版本后再上传网络，从而防止个人图像被未经授权使用。该任务因与个人数据隐私密切相关而受到广泛关注。然而，现有方法仍存在实用性不足的问题，难以在不同实际计算机视觉任务中生成普遍不可利用的样本。为此，本文提出一种新型元跨任务不可利用样本生成框架（MCT-UEG）。其核心是设计了一种面向平坦极小值的元训练与测试方案，以优化生成器，使其能有效生成在广泛任务中均不可被利用的样本。大量实验表明，该框架具有显著有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。