Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks.
Adaku UchenduDaniel CampoyChristopher MenartAlexandra HildenbrandtPublished in: AIKE (2021)
Keyphrases
- jpeg compression
- image watermarking scheme
- white box
- geometric attacks
- watermarking algorithm
- neural network
- image watermarking
- black box
- digital images
- digital image watermarking
- digital watermarking
- genetic algorithm
- neural nets
- pattern recognition
- multilayer perceptron
- multi layer
- maximum likelihood
- source code
- artificial neural networks
- multi agent
- neural network model
- back propagation
- fuzzy logic
- feed forward
- database
- test data
- test cases
- semi fragile watermarking
- malicious users
- high dimensional
- bayesian networks