LDoS attack detection method based on frequency domain feature fusion

Abstract

The invention discloses an LDoS attack detection method based on frequency domain feature fusion, and belongs to the field of computer network security. The method comprises the following steps: firstly, acquiring a network data message in a router to obtain a sample sequence; then, transforming the sample sequence from a time domain to a frequency domain based on discrete Fourier transform and discrete wavelet transform, and fully extracting frequency domain features of the sample sequence; thirdly, performing feature fusion on the extracted frequency domain features by adopting linear discriminant analysis to obtain judgment features, so that the classification performance of the features can be remarkably improved; and finally, inputting the judgment features into a pre-trained single-class classification anomaly detection model, carrying out judgment detection on the network data message in the unit time according to the output of the anomaly detection model, and if the output of the anomaly detection model is-1, judging that the LDoS attack occurs in the network in the unit time. According to the detection method based on frequency domain feature fusion provided by the invention, the LDoS attack can be efficiently, quickly and accurately detected.

Description

technical field [0001] The invention belongs to the field of computer network security, and in particular relates to an LDoS attack detection method based on frequency domain feature fusion. Background technique [0002] Denial of Service (DoS) attack is an attack that damages service availability. The attack attempts to exhaust some important resources related to the service, thereby hindering some normal services provided by the victim system and destroying service availability. DoS attacks do great harm to the network. With the development of DoS attack-related technologies, attack methods and means are becoming more and more diverse and intelligent. The Low-rate Denial of Service (LDoS) attack is a DoS attack variant that has appeared in recent years. Compared with traditional DoS attacks, LDoS attacks are not only more destructive, but also more concealable. [0003] At present, there are two problems in LDoS attack detection: one is that due to the low rate and stro...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the shortcomings of the existing LDoS attack detection methods, such as low detection accuracy and large resource consumption, an LDoS attack detection method based on frequency domain feature fusion is proposed.

Images