DDoS attack detection method based on convolutional neural network

Abstract

The invention discloses a DDoS attack detection method based on the convolutional neural network, wherein the current situation and the development trend of DDoS attack and detection are researched, the principle and the type of the DDoS attack, the working principle of an SVM and a network flow data processing method are analyzed, the convolutional neural network is introduced to train a model, various network security indexes are learned, and the DDoS attack and detection efficiency is improved. Therefore, comprehensive evaluation of the network is realized. The method comprises the following steps: firstly, carrying out Min-Max normalization and PCA dimension reduction processing on data, mapping a preprocessed sample to a high-dimensional feature space through a kernel function, and then introducing a parameter V to control the number of support vectors and error vectors; and then, converting the initial model into a dual model, solving a decision coefficient w and a decision item b, and finally obtaining an optimal classification hyperplane. According to the DDoS attack detection method based on the convolutional neural network, the classification accuracy is improved, the false alarm rate is reduced, the stability and timeliness of the classification model are ensured, the DDoS attack is detected more efficiently, and the risk of network security is reduced.

Description

technical field [0001] The present invention is a distributed denial of service (Distributed Denial of Service, DDoS) attack detection method based on convolutional neural network. The working principle of the product neural network and the method of network flow data processing and anomaly detection of attack traffic belong to the cross field of network security, big data and distributed computing. Background technique [0002] Network-Flows refers to a collection of data packets with the same source port and destination port transmitted between source IP and destination IP within a period of time. It has the characteristics of fast speed, multiple dimensions, and large scale. A single data packet or frame in a network flow has no specific meaning, and it is of practical significance to apply its analysis process to actual network scenarios. Network flow anomaly detection is an important basic part of network flow analysis technology. Flow anomalies usually refer to networ...

AI Technical Summary

Problems solved by technology

[0004] Technical issues: At present, DDoS attack methods are concealed, destructive, and highly organized, making the entire network environment a huge security risk

Images