Abstract
Sensor network intrusion detection has attracted extensive attention. However, previous intrusion detection methods face the highly imbalanced attack class distribution problem, and they may not achieve a satisfactory performance. To solve this problem, we propose a new intrusion detection algorithm based on normalized cut spectral clustering for sensor network in this paper. The main aim is to reduce the imbalance degree among classes in an intrusion detection system. First, we design a normalized cut spectral clustering to reduce the imbalance degree between every two classes in the intrusion detection data set. Second, we train a network intrusion detection classifier on the new data set. Finally, we do extensive experiments and analyze the experimental results in detail. Simulation experiments show that our algorithm can reduce the imbalance degree among classes and reserves the distribution of the original data on the one hand, and improve effectively the detection performance on the other hand.
Highlights
With the development of the wireless sensor network (WSN), human activities have been facilitated greatly in recent years
This paper proposes a Network Intrusion Detection algorithm based on Normalized Cut Spectral Clustering (NIDNCSC) to solve the imbalanced distribution of network connecting behavior
In view of the imbalanced data distribution of network connecting behaviors, we propose a Network Intrusion Detection algorithm based on Normalized Cut Spectral Clustering (NIDNCSC)
Summary
With the development of the wireless sensor network (WSN), human activities have been facilitated greatly in recent years. 5], Gaussian mixture model(GMM) [6], Random Forest(RF) [7], and Support Vector Machines(SVM) [8, 9] etc Such as, MIsmail et al [10] proposed two intrusion detection approaches based on multi-level clustering, which combine spectral clustering (SC) and deep neural network (DNN). This paper proposes a Network Intrusion Detection algorithm based on Normalized Cut Spectral Clustering (NIDNCSC) to solve the imbalanced distribution of network connecting behavior. The main contributions are as follows: Firstly, we select every two classes in the intrusion detection data set to do classification and the algorithm divides the original network connecting samples of the majority class into a relatively small number of clusters.
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