LATIDIA · Ciberseguridad

Cuida tus límites: Ofuscación del modelo consciente de los límites contra el ataque de nodos cruzados

arXiv: 2610.27135v1Tipo de anuncio: nuevo Resumen: Con el avance de los potentes chips de IA, el aprendizaje automático en el dispositivo está ganando terreno por su baja latencia y protección de la privacidad. Sin embargo, cuando los dispositivos de borde están comprometidos

La noticia

arXiv:2610.27135v1 Announce Type: new Abstract: With the advancement of powerful AI chips, on-device machine learning is gaining traction for its low latency and privacy protection. However, when edge devices are compromised, attackers can obtain white-box access to the deployed models by reversing the apps directly to obtain the knowledge of peer devices, which is known as Cross-Node Attacks, like performing efficient adversarial attacks. Most existing defenses target known vulnerabilities, yet white-box access still enables attackers to uncover more unknown weaknesses. This creates a critical risk for edge-device deployments, where one compromised device can endanger all models distributed from the same source. Motivated by findings that the model robustness is primarily