A Novel Scheme for Adversarial Training to Improve the Robustness of DNN Against White Box Attacks.
N. Sai Mani RohithP. P. DeepthiPublished in: CVIP (2) (2022)
Keyphrases
- image watermarking scheme
- white box
- black box
- training process
- watermark embedding
- geometric attacks
- chosen plaintext
- multi agent
- digital images
- wavelet domain
- countermeasures
- image watermarking
- watermarking scheme
- digital image watermarking
- watermarking algorithm
- data sets
- supervised learning
- object oriented
- training set
- training data
- neural network