NeuronInspect: Detecting Backdoors in Neural Networks via Output Explanations.
Xijie HuangMoustafa AlzantotMani B. SrivastavaPublished in: CoRR (2019)
Keyphrases
- neural network
- desired output
- genetic algorithm
- pattern recognition
- artificial neural networks
- hidden units
- hidden structure
- fuzzy logic
- back propagation
- feed forward
- rbf network
- reinforcement learning
- multi layer
- fuzzy systems
- search strategies
- input pattern
- hopfield neural network
- recurrent neural networks
- multilayer perceptron
- self organizing maps
- data mining