LATIDIA · Ciberseguridad

NotaryMark: Marca de agua de múltiples bits para la auditoría de uso de conjuntos de datos de caja negra en modelos de difusión de texto a imagen

arXiv:2611.08985v1 Tipo de anuncio: nuevo Resumen: A medida que los modelos de inteligencia artificial (IA) generativa requieren cada vez más datos, se recopilan y utilizan más datos disponibles públicamente pero con licencia sin autorización. Al

La noticia

arXiv:2611.08985v1 Announce Type: new Abstract: As generative artificial intelligence (AI) models increasingly require data, more publicly available yet licensed data is being harvested and used without authorization. Although several previous studies have proposed watermarking methods for dataset copyright auditing, their applicability to the text-to-image (T2I) setting remains notably limited. The core drawback is that watermarks embedded by existing techniques are often treated as noise and are gradually filtered out and attenuated during the latent noising-denoising process of diffusion model training. We propose NotaryMark, to our knowledge the first multi-bit watermarking method specifically designed for black-box auditing of T2I training dataset use. The core idea of NotaryMark is to align the