Extended Spatially Localized Perturbation GAN (eSLP-GAN) for Robust Adversarial Camouflage Patches †

Deep neural networks (DNNs), especially those used in computer vision, are highly vulnerable to adversarial attacks, such as adversarial perturbations and adversarial patches. Adversarial patches, often considered more appropriate for a real-world attack, are attached to the target object or its sur...

Descripción completa

Detalles Bibliográficos
Autores principales: Kim, Yongsu, Kang, Hyoeun, Suryanto, Naufal, Larasati, Harashta Tatimma, Mukaroh, Afifatul, Kim, Howon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8398873/
https://www.ncbi.nlm.nih.gov/pubmed/34450763
http://dx.doi.org/10.3390/s21165323

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8398873/
https://www.ncbi.nlm.nih.gov/pubmed/34450763
http://dx.doi.org/10.3390/s21165323

Ejemplares similares