LATIDIA · Ciberseguridad

Marcas de agua: de la imposibilidad al cumplimiento auditable

arXiv: 2610.06317v1Tipo de anuncio: nuevo Resumen: El artículo 50 (2) de la Ley de Inteligencia Artificial de la UE requiere que los proveedores de sistemas generativos hagan que las salidas sintéticas sean legibles y detectables por máquina, mientras califican

La noticia

arXiv:2610.06317v1 Announce Type: new Abstract: Article 50 (2) of the EU Artificial Intelligence Act requires providers of generative systems to make synthetic outputs machine-readable and detectable, while qualifying the effectiveness, interoperability, robustness, and reliability by technical feasibility, cost, content-specific limits, and the state of the art. For free-form text, one important implementation route is the implementation of a generative watermarking procedure, which poses a compliance problem that is hard to address. Strong watermarking is impossible against adaptive removal, while ordinary edits attenuate statistical evidence, and unmarked human text may overlap distributionally with machine output. This article develops an auditable alternative. First, it defines a description-length robustness profile. A finite-sample bound