Research on Network Intrusion Detection Technology Based on DCGAN
Chao Wang, Wenhui Wang, Dong Jiahan, Guangxin Guo · 2021
Traditional network intrusion detection algorithms tend to lack learning in a small number of classes due to data imbalance. In reality, intrusion detection systems pay more attention to the detection accuracy of a small number of classes, that is, attack samples. In order to improve the detection accuracy of intrusion detection system, a network intrusion detection method based on deep convolution generative adversarial networks (DCGAN) was proposed. Firstly, the sample data of network intrusion is preprocessed, and the character data set is replaced by image data. Then, DCGAN is used to train and test the sample data. Both the generator and the discriminator are constructed by CNN. The generator is used to construct attack samples, balance the number of training samples, and solve the over fitting problem caused by insufficient training samples. Finally, the trained discriminator is used to test the classification accuracy of samples. Experimental results show that, compared with the traditional algorithm, the proposed algorithm can not only balance the detection accuracy of various types of samples, but also has higher detection accuracy for attack samples.