Black-box Adversarial Attack against Visual Interpreters for Deep Neural Networks.
Yudai HiroseSatoshi OnoPublished in: MVA (2023)
Keyphrases
- black box
- neural network
- rule extraction
- black boxes
- hybrid systems
- white box
- pattern recognition
- visual features
- visual information
- white box testing
- integration testing
- test cases
- fuzzy logic
- multi agent
- neural network model
- recurrent neural networks
- feed forward
- countermeasures
- back propagation
- error rate
- knowledge management
- feedforward neural networks
- case study
- data sets
- database