Guo, J.J., 2020. Design of adaptive marine network intrusion detection and dynamic defense system. In: Guido Aldana, P.A. and Kantamaneni, K. (eds.), Advances in Water Resources, Coastal Management, and Marine Science Technology. Journal of Coastal Research, Special Issue No. 104, pp. 261–265. Coconut Creek (Florida), ISSN 0749-0208.

The shipping network plays an important role in the world's import and export trade, which is easy to be invaded and directly affects the shipping trade between countries. Therefore, it is very important to protect the intrusion effectively. In this paper, we design an adaptive intrusion detection and dynamic defense system. The neural network is used to build the mathematical model of neuron, the learning and training is used to change the network connection weight and topology structure of the sample, so that the output of the network is constantly close to the expected output, the back propagation model of multilayer feed forward network error is built, and the weight of the network system is adjusted until the output error of the network is reduced to an acceptable level, and BP (Back Propagation) is used at the same time The input layer, the hidden layer and the output layer of the propagation neural network are used to train the ocean transportation network, to complete the intrusion detection, and the data packets sent by the attacker are directly shielded by the access control module according to the results, so as to realize the dynamic defense of the intrusion. The simulation results show that the system can effectively detect and defend the intrusion behavior of the outside world, at the same time, the system has a high robustness and a wide range of applicable environments.