Cargando…
Image classification adversarial attack with improved resizing transformation and ensemble models
Convolutional neural networks have achieved great success in computer vision, but incorrect predictions would be output when applying intended perturbations on original input. These human-indistinguishable replicas are called adversarial examples, which on this feature can be used to evaluate networ...
| Autores principales: | , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
PeerJ Inc.
2023
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10403174/ https://www.ncbi.nlm.nih.gov/pubmed/37547405 http://dx.doi.org/10.7717/peerj-cs.1475 |