Xue, D., 2020. Research on identification of illegal intrusion in ship communication network based on depth learning algorithm. In: Bai, X. and Zhou, H. (eds.), Advances in Water Resources, Environmental Protection, and Sustainable Development. Journal of Coastal Research, Special Issue No. 115, pp. 127-129. Coconut Creek (Florida), ISSN 0749-0208.

The intrusion characteristic of ship communication network has wide band and strict stability, which makes it vulnerable to small disturbance in intrusion detection and has poor detection performance. In order to ensure the security of communication, the security mechanism in the network system should be able to scan the system for vulnerabilities, at the same time, it should also be able to monitor, attack and counter-attack the network security in real time, thus intrusion detection system came into being. It is one of the main ways to protect the ship information security to classify the illegal intrusion nodes in the ship communication network. However, with the increase of the number of intrusion nodes, the classification error of the communication network intrusion nodes based on the deep learning algorithm is relatively large, so it is unable to realize the accurate identification and classification of the intrusion nodes. The successful implementation of the method based on deep learning algorithm and cloud computing can effectively improve the accuracy of location judgment of intrusion data and greatly shorten the time required for data feature extraction.