PALADIN : Robust Neural Fingerprinting for Text-to-Image Diffusion Models
This work addresses the need for reliable attribution in text-to-image diffusion models to prevent malicious use, representing a significant advancement over prior methods that lacked full accuracy.
The authors tackled the problem of attributing text-to-image diffusion models with neural fingerprinting to mitigate misuse risks, proposing a method based on cyclic error correcting codes that achieves 100% attribution accuracy, addressing a critical gap where existing methods fall short.
The risk of misusing text-to-image generative models for malicious uses, especially due to the open-source development of such models, has become a serious concern. As a risk mitigation strategy, attributing generative models with neural fingerprinting is emerging as a popular technique. There has been a plethora of recent work that aim for addressing neural fingerprinting. A trade-off between the attribution accuracy and generation quality of such models has been studied extensively. None of the existing methods yet achieved 100% attribution accuracy. However, any model with less than cent percent accuracy is practically non-deployable. In this work, we propose an accurate method to incorporate neural fingerprinting for text-to-image diffusion models leveraging the concepts of cyclic error correcting codes from the literature of coding theory.