Finite Gaussian Neurons: Defending against adversarial attacks by making neural networks say "I don't know".
Félix GrèzesPublished in: CoRR (2023)
Keyphrases
- neural network
- ddos attacks
- back propagation
- activation function
- countermeasures
- hidden layer
- pattern recognition
- learning rules
- artificial neural networks
- neural models
- neural nets
- genetic algorithm
- multi layer
- associative memory
- fuzzy logic
- fault diagnosis
- neural model
- neural network structure
- neural network model
- gaussian mixture model
- self organizing maps
- feed forward
- watermarking scheme
- training process
- privacy preserving
- visual cortex
- hopfield neural network
- maximum likelihood
- hidden neurons