Anti-Prompt: Image Protection against Text-Guided Image-to-Video Generation

Researchers have developed a method called Anti-Prompt designed to protect images from being used as source material for text-to-video generation models. By injecting imperceptible perturbations into a static image, the technique disrupts the ability of AI systems to interpret or animate the content effectively. This approach aims to address rising concerns regarding privacy and copyright infringement as image-to-video tools become more capable of generating unauthorized animations from personal photographs.