2019.11.15 note (2)
Intriguing properties of neural networks
DeepFool: a simple and accurate method to fool deep neural networks
Towards Evaluating the Robustness of Neural Networks
DISTRIBUTIONAL SMOOTHING WITH VIRTUAL ADVERSARIAL TRAINING
ADVERSARIAL TRAINING METHODS FOR SEMI-SUPERVISED TEXT CLASSIFICATION
FREELB: ENHANCED ADVERSARIAL TRAINING FOR LANGUAGE UNDERSTANDING
Attack:
Defense:
In paper, they sample a batch: