A Survey on Efficient Methods for Adversarial Robustness

A Survey on Efficient Methods for Adversarial Robustness

Deep learning has revolutionized computer vision with phenomenal success and widespread applications. Despite impressive results in complex problems, neural networks are susceptible to adversarial attacks: small and imperceptible changes in input space that lead these models to incorrect outputs. Ad...

Full description

Bibliographic Details
Main Authors: Awais Muhammad, Sung-Ho Bae
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Neural networks
deep learning
efficient training
adversarial robustness
adversarial attacks
adversarial learning
Online Access:https://ieeexplore.ieee.org/document/9926085/

Internet

https://ieeexplore.ieee.org/document/9926085/

Similar Items