LATIDIA · Ciberseguridad

Razonamiento limitado: jerarquía cognitiva en la defensa cibernética entre humanos y IA

arXiv: 2610.04878v1Tipo de anuncio: nuevo Resumen: Las evaluaciones humano-agente a menudo comprimen la interacción en una sola puntuación de rendimiento, incluso cuando las políticas humanas y automatizadas se adaptan de manera diferente con el tiempo. Estudiamos esto en un s

La noticia

arXiv:2610.04878v1 Announce Type: new Abstract: Human-agent evaluations often compress interaction into a single performance score, even when human and automated policies adapt differently over time. We study this in a sequential cyber-defense game on an attack graph, where a human or reinforcement-learning defender protects cloud assets against a Deep Q-Network (DQN) attacker. We compare four defender settings: a human reward-only game operationalizing the DQN information structure, a human reward-plus-transition game operationalizing the Cognitive Hierarchy Theory-driven DQN (CHT-DQN) information structure, an automated DQN defender, and an automated CHT-DQN defender. In the reward-only game, participants receive payoff and reward feedback. In the reward-plus-transition game, they also see attacker-aware transition probabilities from the