GoodDiffusion: Proactive Copyright Protection for Diffusion Bridge Models via Learnable Sample-specific Signatures

2026-06-29

AI Summary

This work addresses the lack of proactive copyright protection in diffusion-based generative models by proposing an embedded authorization control mechanism that generates high-quality content only when the input carries a valid signature, otherwise rejecting generation. The core innovation lies in a learnable, sample-specific signature scheme that abandons the universality of traditional static signatures, thereby effectively resisting gradient-based inversion attacks. Furthermore, the authors introduce a backdoor-based selective licensing framework that dynamically assigns signatures conditioned on inputs through a Learnable Signature Network (LSN). Experimental results demonstrate that the proposed method rigorously prevents unauthorized usage while preserving excellent generation quality for authorized users.

Abstract

This paper tackles the challenging problem of developing a proactive copyright protection mechanism that cuts off unauthorized use of diffusion bridge models. Existing studies largely fall into post-hoc attribution (e.g., watermarking and fingerprinting) or degradation-only defenses, which offer only indirect and limited preventive effects. We therefore propose GoodDiffusion, inspired by backdoor mechanisms, to enforce model-level use-time control by internalizing authorization into the generative process through a selectively permissive, otherwise closed behavior. Specifically, GoodDiffusion preserves high-quality generation for authorized queries carrying valid signatures, yet refuses to generate for unauthorized inputs. We further theoretically show that naive static-signature designs (like conventional backdoor injection) are fundamentally fragile, since a surrogate signature can be efficiently recovered via gradient-based optimization. To strengthen security, we introduce a Learnable Signature Network (LSN) that assigns sample-specific signatures conditioned on each input. This breaks the universality of signatures and prevents a surrogate from transferring across inputs. Extensive experiments validate that GoodDiffusion effectively blocks unauthorized use while maintaining strong generation quality for authorized users.

Problem

• copyright protection
• diffusion models
• unauthorized use
• proactive defense
• generative AI

Innovation

• diffusion bridge models
• proactive copyright protection
• learnable signature
• sample-specific signature
• backdoor-based control