Randomized Purifier Based on Low Adversarial Transferability for Adversarial Defense

Randomized Purifier Based on Low Adversarial Transferability for Adversarial Defense

Deep neural networks are generally very vulnerable to adversarial attacks. In order to defend against adversarial attacks in classifiers, Adversarial Purification (AP) was developed to neutralize adversarial perturbations using a generative model at the input stage. AP has an advantage in that it ca...

Full description

Saved in:
Bibliographic Details
Main Authors: Sangjin Park, Yoojin Jung, Byung Cheol Song
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Adversarial attack
adversarial defense
computer vision
deep learning
image classification
security
Online Access:https://ieeexplore.ieee.org/document/10630788/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/10630788/

Similar Items