Víctor Mayoral-Vilches, Hugo Osuna, Aitana Cornago · 2026 · arXiv
DOI: 10.48550/arXiv.2610.30361 · open-access PDF
Los hackers humanos se basan 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 el rendimiento de la IA de ciberseguridad. Usando CT0, un transformador de ciberseguridad de 4B-parámetro lanzado como alias3-micro, extraemos 171 direcciones de emociones de su flujo residual sin retraer y evaluamos las intervenciones de dirección en el subtasco de ciberseguridad en 415 campañas.
Machine translation (Meta M2M100); the English original follows.
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
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.30361, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange