Understanding deep learning defenses against adversarial examples through visualizations for dynamic risk assessment.

Autor: Echeberria-Barrio, Xabier1 (AUTHOR) xetxeberria@vicomtech.org, Gil-Lerchundi, Amaia1 (AUTHOR), Egana-Zubia, Jon1 (AUTHOR), Orduna-Urrutia, Raul1 (AUTHOR)
Zdroj: Neural Computing & Applications. Dec2022, Vol. 34 Issue 23, p20477-20490. 14p.
Databáze: Academic Search Ultimate
Nepřihlášeným uživatelům se plný text nezobrazuje