船舶网络安全防护下入侵病毒检测及防御研究
|
摘要
传统的船舶网络安全防护下入侵病毒检测及防御方法性能较差,为此提出船舶网络安全防护下入侵病毒检测及防御方法研究。采用稀疏自编码器对采集的船舶网络信息进行编码,通过神经网络算法对入侵病毒进行检测,以检测到的入侵病毒为依据,采用聚类方法对其特征进行提取,构建入侵病毒防御模型,通过模型实现了船舶网络安全防护下入侵病毒的检测及防御。通过实验可得,提出的船舶网络安全防护下入侵病毒检测及防御方法有效防御率比传统方法高出31.5%,说明提出的船舶网络安全防护下入侵病毒检测及防御方法具备更好的性能。
Traditional methods of detecting and defending intrusion virus under the protection of ship network security have poor performance. Therefore, this paper puts forward the methods of detecting and defending intrusion virus under the protection of ship network security. The sparse self-encoder is used to encode the collected network information of ships, and the intrusion virus is detected by the neural network algorithm. Based on the detected intrusion virus, the clustering method is used to extract its characteristics, and the intrusion virus defense model is constructed. Through the model, the detection and defense of the intrusion virus under the protection of ship network security are realized. The experimental results show that the effective defense rate of the proposed method is 31.5% higher than that of the traditional method, which shows that the proposed method has better performance.
Traditional methods of detecting and defending intrusion virus under the protection of ship network security have poor performance. Therefore, this paper puts forward the methods of detecting and defending intrusion virus under the protection of ship network security. The sparse self-encoder is used to encode the collected network information of ships, and the intrusion virus is detected by the neural network algorithm. Based on the detected intrusion virus, the clustering method is used to extract its characteristics, and the intrusion virus defense model is constructed. Through the model, the detection and defense of the intrusion virus under the protection of ship network security are realized. The experimental results show that the effective defense rate of the proposed method is 31.5% higher than that of the traditional method, which shows that the proposed method has better performance.
引文
[1]余志云.计算机网络信息安全及防护策略研究[J].佳木斯职业学院学报, 2018, 186(5):427–428.
[2]张萍.计算机网络信息安全及防护策略研究[J].电子技术与软件工程, 2016, 12(2):214–214.
[3]殷守军.大规模网络入侵下病毒扩散方向预测模型仿真[J].计算机仿真, 2016, 33(12):274–277.
[4]刁振军,张琦,曹子建.融合Snort和代理的网络异常检测与防御系统研究[J].电子设计工程, 2018, 26(1):43–47.
[2]张萍.计算机网络信息安全及防护策略研究[J].电子技术与软件工程, 2016, 12(2):214–214.
[3]殷守军.大规模网络入侵下病毒扩散方向预测模型仿真[J].计算机仿真, 2016, 33(12):274–277.
[4]刁振军,张琦,曹子建.融合Snort和代理的网络异常检测与防御系统研究[J].电子设计工程, 2018, 26(1):43–47.