Intrusion detection method based on SVM

Abstract

The invention belongs to the field of pattern recognition and provides an intrusion detection method based on an SVM. The intrusion detection method based on the SVM comprises the following steps of preprocessing data, carrying out feature weighting on the data, carrying out feature extraction on the data and carrying out intrusion detection through the improved SVM. The intrusion detection method based on the SVM reduces the influences of secondary factors on the classification performance, lowers dimensionality, reduces data redundancy information, reduces the operand and improves the classification performance and the intrusion detection accuracy of the SVM.

Description

technical field [0001] The invention relates to the field of pattern recognition, in particular to the field of intrusion detection. Background technique [0002] Intrusion detection is essentially a classification problem, which belongs to the category of pattern recognition. So far, various technologies such as data mining, machine learning, data fusion and neural network have achieved considerable results in intrusion detection, and support vector machine (Support Vector Machine, referred to as SVM) as a new machine learning The method has also achieved certain results. The application of traditional SVM in intrusion detection, although the detection accuracy and efficiency have been improved, but the intrusion detection data has a large amount of data and many dimensions, resulting in a large amount of calculation of the kernel matrix, and some secondary factors will affect its optimal performance. Therefore, the traditional SVM still has application defects. For exam...

AI Technical Summary

Problems solved by technology

The application of traditional SVM in intrusion detection, although the detection accuracy and efficiency have been improved, but the intrusion detection data has a large amount of data and many dimensions, resulting in a large amount of calculation of the kernel matrix, and some secondary factors will affect its optimal performance. The selection of the classification surface, therefore, the traditional SVM still has application defects

For example, it cannot solve the problem of large amount of original data of intrusion detection, high dimensionality, large amount of calculation caused by redundancy, and long training time. The parameters of SVM are not optimized.

Images