Cargando…
Humans can decipher adversarial images
Does the human mind resemble the machine-learning systems that mirror its performance? Convolutional neural networks (CNNs) have achieved human-level benchmarks in classifying novel images. These advances support technologies such as autonomous vehicles and machine diagnosis; but beyond this, they s...
Autores principales: | Zhou, Zhenglong, Firestone, Chaz |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6430776/ https://www.ncbi.nlm.nih.gov/pubmed/30902973 http://dx.doi.org/10.1038/s41467-019-08931-6 |
Ejemplares similares
-
When will AI misclassify? Intuiting failures on natural images
por: Nartker, Makaela, et al.
Publicado: (2023) -
Deepfake detection by human crowds, machines, and machine-informed crowds
por: Groh, Matthew, et al.
Publicado: (2021) -
Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification
por: Wang, Desheng, et al.
Publicado: (2023) -
“Impossible” Somatosensation and the (Ir)rationality of Perception
por: Won, Isabel, et al.
Publicado: (2021) -
Adversarial Data Hiding in Digital Images
por: Wang, Dan, et al.
Publicado: (2022)