LATIDIA · Ciberseguridad

La psicología de un hacker de IA

arXiv: 2610.30361v1Tipo de anuncio: nuevo Resumen: Los hackers humanos confían en la compostura, la persistencia, la vigilancia y la confianza bajo presión. Investigamos si las representaciones de emociones análogas en los modelos de IA pueden mejorar la

La noticia

arXiv:2610.30361v1 Announce Type: new Abstract: Human hackers rely on composure, persistence, vigilance, and confidence under pressure. We investigate whether analogous emotion representations in AI models can improve cybersecurity AI performance. Using CT0, a 4B-parameter cybersecurity transformer released as alias3-micro, we extract 171 emotion directions from its residual stream without retraining and evaluate steering interventions on cybench-subtask across 415 campaigns. Steering toward calm, serene, or desperate improves performance by 1.6 to 2.1 percentage points across ten seeds, while other emotions show limited or negative effects. Results depend strongly on steering direction, layer, and intensity. We further introduce a lightweight context-aware router that selects emotion directions dynamically during execution. With approximately 80