Artwork protection improves by predicting best personalized style defense
How Well Is My Artwork Protected? Predicting and Tailoring Protection against Style Mimicry by Personalization
Cryptography and Security
Summary
Sometimes artists want to protect their digital artwork from being copied or copied badly by AI systems trying to copy their style. The authors found that using one fixed protection method on all artworks works very unevenly—some artworks are better protected than others. They created Patina, a way to quickly test how well different protections work for each artwork and then pick the weakest protection that still works well. This helps artists keep their art safer while causing less visible changes.
What this means in practice
- •For digital artists: Adjust protection strength individually on artworks to prevent AI models from copying styles accurately with less visible change.
- •For digital content platforms: Deploy adaptive artwork protection that predicts and applies personalized defenses to reduce unauthorized style copying by AI.
Authors
Jihye Kang, Jiwon Park, Sungwoo Hwang, Namhyuk Ahn
Abstract
Protection tools add an imperceptible perturbation to each artwork so that a model personalized on it fails to imitate its style, and they apply one recipe, a protection method at a fixed strength, to every artwork. We find that the same recipe protects artworks very differently, well beyond the noise of personalization seeds, and that cheap signals predict this protection before any personalization. Because protection rises and falls together across recipes, our method, Patina, predicts the protection of every recipe from one short trial protection and gives each artwork the weakest recipe whose predicted protection reaches a chosen level. At the same level of visibility, Patina lets more artworks pass the protection threshold than any single recipe and warns the artist about artworks for which no recipe is predicted to pass it.