Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks.
Leo SchwinnRené RaabAn NguyenDario ZancaBjoern M. EskofierPublished in: CoRR (2021)
Keyphrases
- neural network
- pattern recognition
- artificial neural networks
- genetic algorithm
- semi fragile watermarking
- digital image watermarking
- image watermarking
- watermarking scheme
- fuzzy logic
- back propagation
- fault diagnosis
- recurrent neural networks
- sufficient conditions
- fuzzy systems
- watermarking technique
- rough sets
- active learning