Abnormal network flow detection method and device

• Main Authors: SONG SHANGLEI, DONG XUE, HU YUQI, HE LIHUA, WANG SHAOBO, CHENG YUSONG
• Format: Patent
• Language: Chinese; English
• Published: 07.05.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; PHYSICS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention discloses an abnormal network flow detection method and device, and the method comprises the steps: carrying out the data preprocessing of original network flow data, and obtaining multi-domain flow data; wherein the multi-domain flow data comprises time domain data, frequency domain data and time-frequency graph data; performing feature extraction on the multi-domain traffic data by using a parallel convolutional neural network to obtain a time domain feature matrix, a frequency domain feature matrix and a time-frequency graph feature matrix; performing multi-domain feature fusion on the time-domain feature matrix, the frequency-domain feature matrix and the time-frequency graph feature matrix to obtain a multi-domain feature fusion matrix; and performing feature identification according to the multi-domain feature fusion matrix to obtain a classification detection result of the original network traffic data. According to the method, the accuracy of network abnormal traffic detection can be imp