LATIDIA · Ciberseguridad

La exposición del modelo en un dispositivo pone en peligro a otros: repensar la seguridad de la red neuronal perimetral en todos los dispositivos

arXiv: 2610.27152v1Tipo de anuncio: nuevo Resumen: Las redes neuronales (NN) se implementan cada vez más en dispositivos periféricos como plataformas móviles e IoT, ofreciendo baja latencia y privacidad mejorada en comparación con la implementación basada en la nube

La noticia

arXiv:2610.27152v1 Announce Type: new Abstract: Neural networks (NNs) are increasingly deployed on edge devices such as mobile and IoT platforms, offering low latency and improved privacy compared to cloud-based deployment. However, on-device models embedded in mobile applications can be unpacked and exposed to adversaries, enabling cross-node attacks in centrally distributed ecosystems, where adversarial examples crafted on one compromised device transfer effectively to other nodes sharing the same models. To address this threat, we propose VeilNN, a defense framework that reduces adversarial transferability across on-device models via model obfuscation. The core idea of VeilNN is to introduce controlled model diversity while preserving original task functionality. Specifically, VeilNN applies stealthy and irreversible