学术论文信息

 题名:   Real-time DDoS Attack Detection Method for Programmable Device 
 作者:   缪海飞,程光 
 杂志/会议:   IEEE International Conference on Information and Automation 
 卷、期、页码:    
 时间:   2019-06 
 关键词:   DDoS attacks, OpenBox, detection, real time, machine learning 
 摘要:  Aiming at the problem that DDoS (Distributed Denial of Service) attacks are difficult to identify in real time with high accuracy and low energy consumption, a real-time DDoS attack detection method based on programmable device OpenBox is proposed. The method adopts a combination of software and hardware. On the hardware side, OpenBox updates the counter when forwarding packets, and supports user-defined hardware actions. It can provide the feature values required for detection at the hardware level. On the software side, it runs a hardware awareness module based on sliding window and an online detection module based on machine learning. The hardware awareness module senses the network status in real time according to the threshold. When the network is abnormal, the online detection module is launched to detect DDoS attack. A DDoS attack detection prototype system based on this method is implemented, and deployed on OpenBox. Experiments show that the method can detect DDoS attack in real time with low resource occupancy and high accuracy.
 索引:   
 全文链接        导出