Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscation.
Yifan YanXudong PanMi ZhangMin YangPublished in: CoRR (2023)
Keyphrases
- learning models
- white box
- black box
- source code
- machine learning
- learning algorithm
- learning tasks
- loss function
- machine learning algorithms
- semi supervised learning
- neural network
- conditional random fields
- learning problems
- test data
- classification models
- training data
- genetic algorithm
- feature extraction
- case study
- feature selection
- watermarking scheme
- data mining