Prompting Forgetting：通过文本引导实现 GANs 中的遗忘
Prompting Forgetting: Unlearning in GANs via Textual Guidance
AI总结：
本文提出 Text-to-Unlearn 框架，仅通过文本提示即可在预训练 GANs 中选择性地遗忘特征、身份及多属性等概念，无需额外数据集或监督微调，为生成模型的内容移除提供了高效灵活的跨模态解决方案。
摘要：
最先进的生成模型展现出强大的图像生成能力，给托管这些模型的服务提供商带来了各种伦理和法律挑战。因此，内容移除技术（CRTs）已成为一个不断发展的研究领域，旨在无需全面重训练的情况下控制输出。近期的研究探索了在生成模型中使用机器遗忘来解决内容移除问题。然而，此类研究的重点一直放在扩散模型上，而生成对抗网络（GANs）中的遗忘在很大程度上仍未被探索。我们通过提出 Text-to-Unlearn 来填补这一空白，这是一种新颖的框架，仅使用文本提示就能选择性地从预训练 GANs 中遗忘概念，从而在基于人脸训练的模型中实现特征遗忘、身份遗忘以及表情和多属性移除等细粒度任务。利用自然语言描述，我们的方法引导遗忘过程，无需额外数据集或监督微调，提供了一种可扩展且高效的解决方案。为了评估其有效性，我们引入了一种改编自最先进图像-文本对齐度量的自动遗忘评估方法，对遗忘方法提供了全面分析。据我们所知，Text-to-Unlearn 是首个用于 GANs 的跨模态遗忘框架，代表了在管理生成模型行为方面的一项灵活且高效的进步。
英文摘要：
State-of-the-art generative models exhibit powerful image-generation capabilities, introducing various ethical and legal challenges to service providers hosting these models. Consequently, Content Removal Techniques (CRTs) have emerged as a growing area of research to control outputs without full-scale retraining. Recent work has explored the use of Machine Unlearning in generative models to address content removal. However, the focus of such research has been on diffusion models, and unlearning in Generative Adversarial Networks (GANs) has remained largely unexplored. We address this gap by proposing Text-to-Unlearn, a novel framework that selectively unlearns concepts from pre-trained GANs using only text prompts, enabling feature unlearning, identity unlearning, and fine-grained tasks like expression and multi-attribute removal in models trained on human faces. Leveraging natural language descriptions, our approach guides the unlearning process without requiring additional datasets or supervised fine-tuning, offering a scalable and efficient solution. To evaluate its effectiveness, we introduce an automatic unlearning assessment method adapted from state-of-the-art image-text alignment metrics, providing a comprehensive analysis of the unlearning methodology. To our knowledge, Text-to-Unlearn is the first cross-modal unlearning framework for GANs, representing a flexible and efficient advancement in managing generative model behavior.
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。
