Cargando…
Generating adversarial examples without specifying a target model
Adversarial examples are regarded as a security threat to deep learning models, and there are many ways to generate them. However, most existing methods require the query authority of the target during their work. In a more practical situation, the attacker will be easily detected because of too man...
| Autores principales: | , , , , |
|---|---|
| Formato: | Online Artículo Texto |
| Lenguaje: | English |
| Publicado: |
PeerJ Inc.
2021
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8459786/ https://www.ncbi.nlm.nih.gov/pubmed/34616888 http://dx.doi.org/10.7717/peerj-cs.702 |