A novel computer network intrusion detection algorithm based on OSVM and context validation

The current rise in hacking and computer network attacks throughout the world has heightened the demand for improved intrusion detection and prevention solutions. The intrusion detection system (IDS) is critical in identifying abnormalities and assaults on the network, which have grown in size and pervasiveness. The paper proposes a novel approach for network intrusion detection using multistage deep learning image recognition. The network features are transformed into four-channel (Red, Green, Blue, and Alpha) images. The images then are used for classification to train and test the pre-trained deep learning model ResNet50. The proposed approach is evaluated using two publicly available benchmark datasets, UNSW-NB15 and BOUN Ddos. On the UNSW-NB15 dataset, the proposed approach achieves 99.8% accuracy in the detection of the generic attack. On the BOUN DDos dataset, the suggested approach achieves 99.7% accuracy in the detection of the DDos attack and 99.7% accuracy in the detection of the normal traffic.

Download Full-text

STRAD: Network Intrusion Detection Algorithm Based on Zero-Positive Learning in Real Complex Network Environment

10.1109/iscc53001.2021.9631496 ◽

2021 ◽

Author(s):

Ying Zhong ◽

Ziqi Gao ◽

Rui Li ◽

Citong Que ◽

Xinjie Yang ◽

...

Keyword(s):

Intrusion Detection ◽

Complex Network ◽

Detection Algorithm ◽

Network Intrusion Detection ◽

Network Environment ◽

Network Intrusion ◽

Real Complex

Download Full-text

Research on the Network Intrusion Detection Method Introduced with the View of Quantum Optimization

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.380-384.2687 ◽

2013 ◽

Vol 380-384 ◽

pp. 2687-2690

Author(s):

Xiao Jin Zhao

Keyword(s):

Neural Network ◽

Intrusion Detection ◽

Principal Component ◽

Detection Algorithm ◽

Network Intrusion Detection ◽

Large Network ◽

Operating Data ◽

Quantum Neural Network ◽

Network Intrusion ◽

Quantum Optimization

In the process of network intrusion detection, the network operating data need to be counted. Then, the network intrusion detection can be performed through comparing the values of the statistical results with the threshold values of network intrusion detection sequentially. However, too large network operating data will cause the overlapping of operating data during the detection, reducing the accuracy of the network intrusion detection. In order to avoid the defect mentioned above, a large data network intrusion detection algorithm introduced with quantum optimization neural network is proposed. Through the analysis of the principal component of the data, the process of the massive network operating data can be simplified. Using the quantum neural network method, the initial threshold of network intrusion feature can be achieved, so as to provide accurate data base for the network intrusion detection. Taking the advantage of small distance parade of genetic algorithms, the threshold characteristic is optimized and the mass redundancy interference characteristic is overcome, so as to fulfill the network intrusion detection. Experimental results show that the proposed algorithm used for network intrusion detection can improve the accuracy of detection effectively and achieve satisfactory results.

Download Full-text