High-speed rail operating environment recognition based on neural network and adversarial training

Neural network is one of the key technologies for deep learning. Experiments on some standard test datasets show that their recognition ability has reached the level of human beings. However, they are extremely vulnerable to adversarial examples, that is, adding some subtle perturbations to the input example can cause the model to give a wrong output with high confidence. In this paper, we propose a non-contact approach based on neural network and adversarial training to recognize the high-speed rail operating environment. We first built the environment dataset and trained neural network models to do the recognition. We found that our model had high prediction accuracy, but with poor security since it was easy to attack our model using Basic Iterative Methods (BIM). To improve its security, we performed adversarial training based on the adversarial training dataset we built. The evaluation experiments indicated that this approach could improve the security of our model at the same time ensuring the prediction accuracy on the original test dataset.