An empirical intrusion detection system based on XGBoost and bidirectional long‐short term model for 5G and other telecommunication technologies. (23rd January 2022)

• Record Type: Journal Article
• Authors: Karthikraja, Chinnathangam; Senthilkumar, Jayaprakasam; Hariharan, Rajadurai; Usha Devi, Gandhi; Suresh, Yuvaraj; Mohanraj, Vijayakumar
• Is Part Of: Computational intelligence. Volume 38:Number 4(2022)
• Page Start: 1216
• Page End: 1231
• Publication Date: 2022-01-23
• Subjects: bidirectional long short term model -- intrusion detection system -- NDL‐KDD -- XGBoost; Artificial intelligence -- Periodicals; Computational linguistics -- Periodicals; 006.3
• DOI: 10.1111/coin.12497
• Languages: English
• ISSNs: 0824-7935

Abstract

Abstract: Recently, intrusion detection system (IDS) has become an essential remedy to protect networks from malicious activities and attacks. The attacks force the network activities under risk and cause network data as an unrecoverable one. The attacks have different features in nature and their detection rate is low. An efficient attack detection system requires a huge volume of network transactions and relevant features for training. But the existing datasets have significant and nonsignificant features together. Hence, the significant feature selection plays a major role to detect the attacks. For this reason, this paper adopts the XGBoost approach to identify the relevant (significant) features of the attacks in the dataset. After this XGBoost, this article applies the bidirectional long short term model (Bi‐LSTM) for the detection and classification of the attacks. This Bi‐LSTM model is a novel approach to the IDS and very effective to increase the detection rate. Thus, this article focuses on feature reduction and classification of the attacks. The experimental results show that the proposed XGBoost and Bi‐LSTM combination outperforms in detecting attacks.