PALADIN : Robust Neural Fingerprinting for Text-to-Image Diffusion Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: L, Murthy, Tripathi, Subarna
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913958107021312
author L, Murthy
Tripathi, Subarna
author_facet L, Murthy
Tripathi, Subarna
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03170
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PALADIN : Robust Neural Fingerprinting for Text-to-Image Diffusion Models
L, Murthy
Tripathi, Subarna
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
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.
title PALADIN : Robust Neural Fingerprinting for Text-to-Image Diffusion Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2506.03170