Fostering The Robustness Of White-Box Deep Neural Network Watermarks By Neuron Alignment.
Fang-Qi LiShi-Lin WangYun ZhuPublished in: ICASSP (2022)
Keyphrases
- neural network
- white box
- black box
- semi fragile watermarking
- source code
- neural model
- digital images
- neuron model
- genetic algorithm
- back propagation
- activation function
- neural network model
- associative memory
- artificial neural networks
- wavelet domain
- spread spectrum
- network architecture
- watermarking scheme
- multilayer perceptron
- neural nets
- digital watermarking
- data sets
- spiking neurons
- source code metrics
- gradient vector
- neural models
- watermark embedding
- input pattern
- knowledge building
- query language
- training data