Survey on leveraging uncertainty estimation towards trustworthy deep neural networks: The case of reject option and post-training processing
Although neural networks (especially deep neural networks) have achieved\textit {better-
than-human} performance in many fields, their real-world deployment is still questionable …
than-human} performance in many fields, their real-world deployment is still questionable …
Defending wireless receivers against adversarial attacks on modulation classifiers
PF de Araujo-Filho, G Kaddoum… - IEEE Internet of …, 2023 - ieeexplore.ieee.org
Deep learning has been adopted for a wide range of wireless communication tasks,
including modulation classification, because of its great classification capability. However …
including modulation classification, because of its great classification capability. However …
Towards intelligent security mechanisms for connected things
P Freitas de Araujo Filho - 2023 - espace.etsmtl.ca
La nature de diffusion des communications sans fil et l'adoption généralisée des objets
connectés augmentent les surfaces d'attaque et permettent aux attaquants de lancer …
connectés augmentent les surfaces d'attaque et permettent aux attaquants de lancer …