Guiding the retraining of convolutional neural networks against adversarial inputs

BACKGROUND: When using deep learning models, one of the most critical vulnerabilities is their exposure to adversarial inputs, which can cause wrong decisions (e.g., incorrect classification of an image) with minor perturbations. To address this vulnerability, it becomes necessary to retrain the aff...

Descripción completa

Detalles Bibliográficos
Autores principales: Durán, Francisco, Martínez-Fernández, Silverio, Felderer, Michael, Franch, Xavier
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2023
Materias:
Artificial Intelligence
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10495969/
https://www.ncbi.nlm.nih.gov/pubmed/37705636
http://dx.doi.org/10.7717/peerj-cs.1454

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10495969/
https://www.ncbi.nlm.nih.gov/pubmed/37705636
http://dx.doi.org/10.7717/peerj-cs.1454

Ejemplares similares