Name
Abstract | ||
|---|---|---|
Since software-defined networking (SDN) has the ad-vantages of central control programmability and global view, it is suitable for industrial network. However, large-scale security risks such as distributed denial of service (DDoS) attacks endanger the security and reliability of services in the SDN-based system. Therefore, a comprehensive and efficient solution to this issue is crucial. This paper proposes a scheme for mitigating DDoS attack traffic deployed on an SDN application plane. The framework periodically obtains the traffic statistics of the switch ports and flow tables. After obtaining the traffic characteristics, a machine learning model is used for training. The trained model can identify benign and malicious traffic. After the attack is found, the rules are sent to the switch to control the flow and resist DDoS attacks. We use the CICDDoS2019 dataset to perform experiments. The experimental results show that compared to other schemes, the proposed scheme achieves more accurate classification. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/HPCC-DSS-SmartCity-DependSys53884.2021.00059 | 2021 IEEE 23rd Int Conf on High Performance Computing & Communications; 7th Int Conf on Data Science & Systems; 19th Int Conf on Smart City; 7th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC/DSS/SmartCity/DependSys) |
Keywords | DocType | ISBN |
SDN,DDoS attacks,security,Renyi entropy,machine learning | Conference | 978-1-6654-9458-8 |
Citations | PageRank | References |
0 | 0.34 | 17 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hong Zhong | 1 | 208 | 33.15 |
| Chao Yu | 2 | 0 | 0.34 |
| Jie Cui | 3 | 16 | 8.88 |
| Xiuwen Sun | 4 | 0 | 0.68 |
| Chengjie Gu | 5 | 0 | 0.34 |
| Lu Liu | 6 | 215 | 27.61 |