How to Evaluate and Mitigate IP Infringement in Visual Generative AI?

The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered that the state-of-the-art visual generative models can generate content that bears a striking resemblance to characters protected by intellectual property rights held by major entertainment companies (such as Sony, Marvel, and Nintendo), which raises potential legal concerns. This happens when the input prompt contains the character's name or even just descriptive details about their characteristics. To mitigate such IP infringement problems, we also propose a defense method against it. In detail, we develop a revised generation paradigm that can identify potentially infringing generated content and prevent IP infringement by utilizing guidance techniques during the diffusion process. It has the capability to recognize generated content that may be infringing on intellectual property rights, and mitigate such infringement by employing guidance methods throughout the diffusion process without retrain or fine-tune the pretrained models. Experiments on well-known character IPs like Spider-Man, Iron Man, and Superman demonstrate the effectiveness of the proposed defense method.

Generative AI can now create lifelike images from simple text. But sometimes, they accidentally produce pictures that look too much like famous characters from movies or games — even without naming them. This can lead to legal issues. Our research shows how common this problem is, and we introduce a simple way to stop it. We built a system that checks what the AI creates and gently guides it to avoid copying well-known characters, without hurting image quality. This helps make AI image generation safer and more responsible for everyone.