<ul><li>State-of-the-art generative models pose ethical and legal challenges to service providers.</li><li>Text-to-Unlearn is a framework that selectively unlearns concepts from pre-trained GANs using text prompts.</li><li>It enables feature unlearning, identity unlearning, and tasks like expression and multi-attribute removal.</li><li>Text-to-Unlearn offers a scalable and efficient solution without requiring additional datasets or fine-tuning.</li></ul>

Prompting Forgetting: Unlearning in GANs via Textual Guidance

Discover more