Improving the Adversarial Robustness of Neural ODE Image Classifiers by Tuning the Tolerance Parameter

Improving the Adversarial Robustness of Neural ODE Image Classifiers by Tuning the Tolerance Parameter

The adoption of deep learning-based solutions practically pervades all the diverse areas of our everyday life, showing improved performances with respect to other classical systems. Since many applications deal with sensible data and procedures, a strong demand to know the actual reliability of such...

Full description

Bibliographic Details
Main Authors: Fabio Carrara, Roberto Caldelli, Fabrizio Falchi, Giuseppe Amato
Format: Article
Language:English
Published: MDPI AG 2022-11-01
Series:Information
Subjects:
neural ordinary differential equation
adversarial defense
image classification
Online Access:https://www.mdpi.com/2078-2489/13/12/555

Internet

https://www.mdpi.com/2078-2489/13/12/555

Similar Items