An efficient intrusion detection model based on deepFM
Yuchen Ji, Xiaoyong Li · 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · 2020
With the development of the Internet, more and more network attacks are also emerging. The traditional intrusion detection system has been challenged tremendously, and it is unable to detect the new types of attacks. This paper proposes an intrusion detection model based on deepFM, which combines the advantages of FM algorithm for processing shallow features and the advantages of deep neural network for processing deep features, which can effectively extract features and classify them. We then performed experiments using the KDD CUP 99 dataset. First, the training set is deduplicated and oversampled to balance various types of samples, and then the processed data is used for training. Then optimize tuning parameters and find an optimal model. Finally, use the best model to make predictions on the test set. On the test set, we got a correct rate of 0.934 and a COST value of 0.191. By analyzing the results and comparing existing studies, we can conclude that the model proposed in this paper has a good effect on KDD 99 CUP and has certain practical value.