LATIDIA · Ciberseguridad

Agentes del caos: una sistematización del conocimiento (SoK) sobre ataques maliciosos a sistemas de IA genéticos

arXiv: 2611.10843v1Tipo de anuncio: nuevo Resumen: Los sistemas de IA genéticos amplían los modelos de lenguaje grandes con herramientas, memoria, recuperación, interfaces de uso de navegador o computadora, ejecución de código, servicios externos y coordi multiagente

La noticia

arXiv:2611.10843v1 Announce Type: new Abstract: Agentic AI systems extend large language models with tools, memory, retrieval, browser or computer-use interfaces, code execution, external services, and multi-agent coordination. Although these capabilities enable agents to act beyond text generation and perform tasks, they also create attack paths through which adversaries can exploit untrusted content, deceptive metadata, poisoned state, compromised skills, mutable dependencies, or malicious code. Such attacks can manipulate planning and tool use, corrupt memory, abuse code-execution environments, and trigger harmful downstream effects. In this paper, we present a systematic review of malicious attacks targeting agentic AI systems. We screened 186 candidate sources and retained 98. Following independent coding and resolver adjudication,