作者: Chih-Chieh Chen , Yi-Ren Chen , Wei-Chih Lu , Shi-Chun Tsai , Ming-Chuan Yang
DOI: 10.1109/DESEC.2017.8073807
关键词: Network packet 、 Denial-of-service attack 、 Application layer DDoS attack 、 Computer security 、 Ip address 、 Classifier (UML) 、 Engineering 、 Computer network 、 Software-defined networking 、 Network service
摘要: Distributed denial of service (DDoS) is an attack that attempts to disrupt network for various malicious purposes. It makes use public services as reflectors amplify the traffic, and thus called distributed reflection attacks. This type forges source IP address, it hard filter problematic packets. With Software Defined Networking (SDN) machine learning techniques, we implement a system detect DRDoS packets block amplification attacks automatically. DNS NTP amplifications are two typical DDoS. By analyzing traffic features, although our classifier trained only attack, can identify then both with great accuracy.