research
∙
12/29/2021
Repairing Adversarial Texts through Perturbation
It is known that neural networks are subject to attacks through adversar...
share
research
∙
07/17/2021
Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
Although deep learning has demonstrated astonishing performance in many ...
research
∙
12/03/2020
Towards Repairing Neural Networks Correctly
Neural networks are increasingly applied to support decision making in s...
research
∙
09/22/2019
Analyzing Recurrent Neural Network by Probabilistic Abstraction
Neural network is becoming the dominant approach for solving many real-w...
research
∙
12/14/2018