Mitigating Adversarial Attacks for Deep Neural Networks by Input Deformation and Augmentation.
Pengfei QiuQian WangDongsheng WangYongqiang LyuZhaojun LuGang QuPublished in: ASP-DAC (2020)
Keyphrases
- neural network
- desired output
- pattern recognition
- artificial neural networks
- genetic algorithm
- multi layer
- fuzzy logic
- input pattern
- fault diagnosis
- input data
- multilayer perceptron
- neural network model
- data sets
- malicious attacks
- security risks
- traffic analysis
- deep learning
- countermeasures
- feed forward
- intrusion detection
- image registration
- expert systems
- decision trees
- computer vision