LATIDIA · Ciberseguridad

Moirae: un marco colaborativo de agentes multimodales para la detección dinámica de malware en Android

arXiv: 2608.27994v2Announce Type: replace Resumen: El ecosistema Android se enfrenta a amenazas de malware persistentes y en rápida evolución. Los detectores de aprendizaje automático existentes son vulnerables a la deriva del concepto porque dependen de

La noticia

arXiv:2608.27994v2 Announce Type: replace Abstract: The Android ecosystem faces persistent and rapidly evolving malware threats. Existing machine learning detectors are vulnerable to concept drift because they rely on implementation-specific features whose distributions change over time. Large language models (LLMs) offer strong semantic understanding and zero-shot reasoning, but current LLM-based detectors typically depend on code-centric or single-dimensional evidence, making them susceptible to obfuscation and limiting comprehensive behavior analysis. We present {\sysname}, a multimodal agent collaborative framework for dynamic Android malware detection. {\sysname} dynamically collects multimodal runtime evidence and employs ReAct-based specialized agents to analyze complementary behavioral views. The detection process begins by identifying visual deception cues, modeling UI state transitions, and