LATIDIA · Ciberseguridad

Mejora de la seguridad del sistema de IA en el borde con un controlador de seguridad de hardware apilado para una detección de anomalías robusta y energéticamente eficiente.

arXiv:2611.01150v1 Anuncio Tipo: nuevo Resumen: En los últimos años, la creciente adopción de sistemas de IA en el borde ha estado acompañada de un aumento en las amenazas de seguridad. Las implementaciones de IA en el borde se enfrentan a un espectro de seguridad en rápida evolución.

La noticia

arXiv:2611.01150v1 Announce Type: new Abstract: In recent years, the growing adoption of Edge AI systems has been accompanied by a surge in security threats. Edge AI deployments face an rapidly evolving spectrum of security threats, from side-channel information leakage to ad- versarial model manipulation and physical device tampering. Conventional security mechanisms such as malware scanners and resource-intensive firewall solutions are unsuitable due to edge AIs typically limited computational resources, strict energy budgets and thermal constraints especially in battery-powered and field-deployed environments. This paper proposes a stacked, hardware-based security mechanism that enables low-overhead, continuous detection of anomalous execution patterns. Anomaly detection utilizing hard- ware performance counters and physical sensors outperforms software-based