LATIDIA · Ciberseguridad

Revisión de los riesgos de privacidad en las redes neuronales profundas cuantificadas

arXiv:2610.37488v1 Anuncio Tipo: nuevo Resumen: La cuantización de modelos se ha convertido en una técnica fundamental para permitir el despliegue eficiente de redes neuronales profundas (DNN) a gran escala en aplicaciones intensivas en datos mediante red

La noticia

arXiv:2610.37488v1 Announce Type: new Abstract: Model quantization has become a fundamental technique for enabling the efficient deployment of large-scale deep neural networks (DNNs) in data-intensive applications by reducing model size. Despite its widespread adoption, the impact of quantization on training data privacy --- particularly vulnerability to membership inference attacks (MIAs) --- remains largely unexplored. In this paper, we present the first comprehensive empirical study of privacy risks in quantized DNNs, evaluating eight state-of-the-art MIA attacks across six representative quantization methods. Our results reveal that practical quantization levels (4-8 bits) have limited impact on membership privacy risks, with quantized models remaining largely as vulnerable as their full-precision counterparts. Although aggressive low-bit