Training for Faster Adversarial Robustness Verification via Inducing ReLU Stability.
Kai Yuanqing XiaoVincent TjengNur Muhammad (Mahi) ShafiullahAleksander MadryPublished in: ICLR (Poster) (2019)
Keyphrases
- neural network
- real time
- training algorithm
- multi agent
- training set
- computational efficiency
- asymptotic stability
- signature verification
- stability analysis
- feedforward neural networks
- face verification
- training phase
- training examples
- training samples
- supervised learning
- hidden markov models
- genetic algorithm
- real world