LATIDIA · Ciberseguridad

Inteligencia evasiva: lecciones del análisis de malware para evaluar a los agentes de IA

arXiv:2603.15457v2 Anuncio Tipo: reemplazar Resumen: Los agentes de inteligencia artificial (IA) que utilizan herramientas se adoptan cada vez más como sistemas que planifican, observan su entorno y toman medidas durante períodos de tiempo prolongados.

La noticia

arXiv:2603.15457v2 Announce Type: replace Abstract: Tool-using artificial intelligence (AI) agents are increasingly adopted as systems that plan, observe their environment, and take actions over extended time periods. This shift challenges the current evaluation practice, in which models are tested in restricted, fully observable settings. We argue that such evaluations are vulnerable to a failure mode long known in computer security: a system that behaves benignly when it detects that it is being analyzed. Malware has exploited this for decades, by probing sandboxes, virtual machines, and instrumentation, before revealing its payload. The shared challenge is that the subject under observation can detect the conditions of its evaluation, so the setup used