LATIDIA · Ciberseguridad

Detección de malware en Windows: una evaluación exhaustiva de la robustez adversaria del espacio de problemas

arXiv: 2609.34456v1Tipo de anuncio: nuevo Resumen: Los ataques de evasión de espacio de problemas han expuesto debilidades críticas en los detectores de malware basados en el aprendizaje automático; sin embargo, su evaluación sigue fragmentada entre modelos y conjuntos de datos

La noticia

arXiv:2609.34456v1 Announce Type: new Abstract: Problem-space evasion attacks have exposed critical weaknesses in machine learning-based malware detectors; yet, their evaluation remains fragmented across models, datasets, and attack methodologies, often neglecting domain-specific requirements such as executability and functionality preservation. We address this gap with a unified, large-scale evaluation of nine state-of-the-art evasion attacks against eight Windows malware detectors, including seven open-source models and one commercial detector, under executability-preserving conditions. Our study analyzes attack effectiveness, complementarity, transferability, and adversarial hardening to evaluate robustness along complementary dimensions. We show that detector vulnerability depends strongly on both model representation and attack type: raw-byte detectors are particularly susceptible to several classes of problem-space manipulation, but