Support Vector Machine Intrusion Detection Scheme Based on Cloud-Fog Collaboration

Fog computing is a new computing paradigm in the era of the Internet of Things. Aiming at the problem that fog nodes are closer to user equipment, with heterogeneous nodes, limited storage capacity resources, and greater vulnerability to intrusion, a lightweight support vector machine intrusion detection model based on Cloud-Fog Collaboration(CFC-SVM) is proposed. Due to the high dimensionality of network data, first, Principal Component Analysis (PCA) is used to reduce the dimensionality of the data, eliminate the correlation between attributes and reduce the training time. Then, in the cloud server, a support vector machine (SVM) optimized by the particle swarm algorithm is used to complete the training of the dataset, obtain the optimal SVM intrusion-detection classifier, send it to the fog node, and carry out attack detection at the fog node. Experiments with the classic KDD CUP 99 dataset show that the model in this paper is better than other similar algorithms in regard to detection time, detection rate and accuracy, which can effectively solve the problem of intrusion detection in the fog environment.

Automated summary

This paper proposes a lightweight support vector machine intrusion detection model based on Cloud-Fog Collaboration(CFC-SVM), which addresses the issues of fog nodes being closer to user equipment, having heterogeneous nodes, limited storage capacity resources, and greater vulnerability to intrusion. The model utilizes Principal Component Analysis (PCA) to reduce dimensionality, eliminates attribute correlation, and reduces training time. Experimental results using the KDD CUP 99 dataset demonstrate that the proposed model outperforms other similar algorithms in terms of detection time, detection rate, and accuracy, effectively solving the problem of intrusion detection in the fog environment.