Defending CNN Against FGSM Attacks Using Beta-Based Personalized Activation Functions and Adversarial Training

Defending CNN Against FGSM Attacks Using Beta-Based Personalized Activation Functions and Adversarial Training

Machine learning algorithms based on deep neural networks have been widely used in many fields especially in computer vision, with impressive results. However, these models are vulnerable to different types of attacks like adversarial ones, which require attention to the model security and confident...

Full description

Saved in:
Bibliographic Details
Main Authors: Hanen Issaoui, Asma Eladel, Ahmed Zouinkhi, Mourad Zaied, Lazhar Khriji, Sarvar Hussain Nengroo
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Activation function
Beta function
CNN model security adversarial attacks
FGSM
Online Access:https://ieeexplore.ieee.org/document/10606465/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10606465/

Similar Items