一种基于超球面嵌入的僵尸网络检测方法、装置及设备
By combining hyperspherical embedding and Extreme Learning Machine (ELM) classifier, high-precision classification of botnet traffic is achieved, solving the problem of insufficient accuracy of botnet detection in complex encryption scenarios in existing technologies, and improving the real-time performance and intelligence level of network security protection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SOUTHEAST UNIV
- Filing Date
- 2025-09-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing DDoS detection methods struggle to achieve high-precision classification in complex encryption scenarios and lack the ability to distinguish between different botnet families, resulting in a lack of initiative and foresight in network protection systems.
A botnet detection method based on hyperspherical embedding is adopted. By acquiring traffic feature vectors and mapping them to a unit spherical space, the method is classified by combining an Extreme Learning Machine (ELM) classifier. The botnet family prototype vectors are extracted by spherical clustering and von Mises-Fisher hybrid model, and a geometric representation of high-dimensional features and label correspondence is constructed.
It improves the accuracy and real-time performance of botnet family classification, enhances the ability to detect unknown or variant botnets in complex environments, and improves the refinement and intelligence of the network security protection system.
Smart Images
Figure CN121193478B_ABST
Abstract
Citation Information
Patent Citations
Botnet recognition method based on extreme learning machine
CN111224998A
Botnet detection method and system based on feature selection and feature fusion
CN119324809A