LATIDIA · Ciberseguridad

TERMon: Detección de amenazas de comportamiento persistentes en Edge AI a través de un monitor de tiempo de ejecución ternario nativo del hardware

arXiv: 2609.21713v1Tipo de anuncio: nuevo Resumen: Los aceleradores Edge AI se implementan cada vez más en entornos críticos para la seguridad, donde las salidas del modelo pueden controlar los actuadores físicos, tomar decisiones de control de acceso o desencadenar

La noticia

arXiv:2609.21713v1 Announce Type: new Abstract: Edge AI accelerators are increasingly deployed in safety-critical environments, where model outputs may control physical actuators, make access-control decisions, or trigger alarms. In these settings, runtime failures often remain undetected because model corruption, distribution shift, and adversarial inputs can still produce well-formed, confident predictions. This paper presents TERMon, a lightweight hardware runtime monitor that detects such anomalies by observing inference behavior rather than re-executing or formally verifying the model. TERMon represents class-conditional trusted behavior as hardware-efficient ternary patterns that are matched in parallel against a thermometer-encoded fingerprint. The ternary encoding reproduces the corresponding unquantized range decision exactly. TERMon detects harmful weight corruptions in proportion to