LATIDIA · Ciberseguridad

Lavado de datos: evadir la auditoría de uso de datos en grandes modelos lingüísticos

arXiv:2611.09446v1 Anuncio Tipo: nuevo Resumen: La auditoría del uso de datos en los modelos de lenguaje grandes (LLM) tiene como objetivo determinar si los datos proporcionados se han utilizado para el entrenamiento, lo que respalda las salvaguardas de la propiedad de los datos. Un dominio

La noticia

arXiv:2611.09446v1 Announce Type: new Abstract: Data-use auditing in Large Language Models (LLMs) aims to determine whether the given data has been used for training, thereby supporting data ownership safeguards. A dominant solution is data watermarking, which embeds traceable signals into training data and detects them in model outputs. Recent studies have proposed many watermarking-based auditing methods in LLMs. However, systematic investigation from an adversarial perspective remains limited: non-compliant LLM providers would use unauthorized copyrighted datasets for training their own models to enhance model capabilities, while attempting to evade detection by auditors, thereby avoiding legal liability. To fill this research gap, we propose a novel evasion framework, termed Logit Laundering, where