LATIDIA · Ciberseguridad

Hacia agentes de IA conscientes de la seguridad en escenarios de ataque de ingeniería social realistas

arXiv: 2611.10037v1Tipo de anuncio: nuevo Resumen: Los agentes personales de IA se despliegan cada vez más en los dispositivos de los usuarios para ejecutar acciones que involucran dinero real y datos confidenciales, pero su seguridad bajo ataques de ingeniería social

La noticia

arXiv:2611.10037v1 Announce Type: new Abstract: Personal AI agents are increasingly deployed on user devices to execute actions involving real money and sensitive data, but their security under social engineering attacks has not been systematically evaluated. We propose SEA (Social Engineering Attack Benchmark), the first interactive environment for evaluating the intrinsic security capability of AI agents in social engineering attack scenarios, covering 8 daily-life domains, 30+ simulated applications, a 4-level difficulty gradient, and a 5-dimensional evaluation framework, with 320 evaluation tasks designed in consultation with anti-fraud specialists and spanning two culturally distinct settings in Chinese and English. Evaluation on 11 frontier open-source and closed-source models, with GPT-6 evaluated only in Chinese,