Adversarial catoptric light: An effective, stealthy and robust physical‐world attack to DNNs
Abstract Recent studies have demonstrated that finely tuned deep neural networks (DNNs) are susceptible to adversarial attacks. Conventional physical attacks employ stickers as perturbations, achieving robust adversarial effects but compromising stealthiness. Recent innovations utilise light beams,...
Na minha lista:
| Principais autores: | , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
Wiley
2024-08-01
|
| coleção: | IET Computer Vision |
| Assuntos: | |
| Acesso em linha: | https://doi.org/10.1049/cvi2.12264 |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|