From Concept Erasure to Style Purification: Contrastive Eigenbases for Artist Style Protection

תקציר מקורי באנגליתarXiv:2602.08059v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models can reproduce specific artists visual styles at extremely low cost, raising copyright and deployment safety concerns about unauthorized style mimicry. Existing model-side protection methods generally follow ordinary concept erasure, emphasizing aggressive deletion or redirection of target styles. However, our causal intervention analysis shows that the central issue is not insufficient erasure strength, but a mismatch between artist styles and this paradigm: unlike ordinary object concepts, artist styles do not form compact, localized editable semantic units. Consequently, sparse editing and fixed retain lists struggle to suppress target styles while preserving generation utility. We therefore reformul