Translate 
Chat Pdf 
Abstract
Network intrusion detection system (NIDS) is a commonly used tool to detect attacks and protect networks, while one of its general limitations is the false positive issue. On the basis of our comparative experiments and analysis for the characteristics of the particle swarm optimization (PSO) and Xgboost, this paper proposes the PSO-Xgboost model given its overall higher classification accuracy than other alternative models such like Xgboost, Random Forest, Bagging and Adaboost. Firstly, a classification model based on Xgboost is constructed, and then PSO is used to adaptively search for the optimal structure of Xgboost. The benchmark NSL-KDD dataset is used to evaluate the proposed model. Our experimental results demonstrate that PSO-Xgboost model outperforms other comparative models in precision, recall, macro-average (macro) and mean average precision (mAP), especially when identifying minority groups of attacks like U2R and R2L. This work also provides experimental arguments for the application of swarm intelligence in NIDS.
Highlights
With the rapid development of the Internet, artificial intelligence and big data technologies, network security confronts more complicated threats than ever before
The results showed the effectiveness of the chaotic dolphin swarm algorithm (CDSA) based on Kent map
The results showed that the based PSO (BPSO)-standard-based PSO (SPSO)-support vector machine (SVM) model achieved higher detection accuracy and lower false alarm rates (FARs)
Summary
With the rapid development of the Internet, artificial intelligence and big data technologies, network security confronts more complicated threats than ever before. Researchers in related fields have achieved remarkable advancements to improve NIDS by introducing machine learning, data mining, and other technologies to the systems, such as the restricted Boltzmann machines applied to Dos attack detection [3], artificial immune system approaches [4], and the application of autoencoder and SVM [5]. The main contributions of this work are as follows: 1) We develop a novel model PSO-Xgboost based on Xgboost by using PSO to adaptively optimize its parameters This can effectively improve the performance of network intrusion detection, including the improvement of the detection accuracy of various types of attacks, especially on minority groups of attacks.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
