Malicious traffic detection method based on GAN sample enhancement

• Main Authors: GUO YULING, WANG YING, CHANG JIE, ZENG SIMING, ZUO XIAOJUN, XI BO, SHI LIPENG, HOU BOTAO, LIU HUIYING, LIU SHUO, CHEN ZE
• Format: Patent
• Language: Chinese; English
• Published: 26.04.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC COMMUNICATION TECHNIQUE; ELECTRICITY; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHICCOMMUNICATION

The invention relates to a malicious traffic detection method based on GAN sample enhancement. According to the method, an original data set is detected after being processed by a data preprocessing module, a GAN-based malicious traffic generation module, a serial feature selection module and a CatBoost algorithm-based malicious traffic detection module in sequence, and a detection result is obtained. The method aims at solving the problems that network flow data are unbalanced, feature selection excessively depends on expert experience, the detection false alarm rate is high, and the accuracy rate is low. 本发明涉及一种基于GAN样本增强的恶意流量检测方法，该方法为原始数据集依次经由数据预处理模块、基于GAN恶意流量生成模块、串行特征选择模块以及基于CatBoost算法的恶意流量检测模块处理后进行检测并获得检测结果。本发明旨在解决网络流量数据不平衡问题，特征选择过度依赖于专家经验问题和检测误报率高、准确率低的问题。