Sparse Attacks for Manipulating Explanations in Deep Neural Network Models.
Ahmad AjalloeianSeyed-Mohsen Moosavi-DezfooliMichalis VlachosPascal FrossardPublished in: ICDM (2023)
Keyphrases
- neural network model
- neural network
- artificial neural networks
- countermeasures
- sparse representation
- network architecture
- input variables
- neural models
- multilayer perceptron
- bp neural network
- rbf neural network
- watermarking scheme
- information security
- fuzzy logic
- growing neural gas
- multi layer perceptron
- bayesian models
- long term
- generating explanations