Abstract | ||
---|---|---|
The technological advancement in VoIP technology and P2P streaming led to the development of novel applications. Most of these applications use UDP traffic. The availability of UDP services for applications such as streaming, trivial file transfer, are denied to legitimate users due to malicious traffic, intentionally created by abnormal requesting behaviour of the botnets. Categorizing the traffic is required to discriminate the malicious traffic that occur due to attacks from normal traffic for better real time resource allocation. For this purpose, this paper proposes a two level hybrid classification model based on incremental learning to detect high and low rate attacks that deny the legitimate access to connectionless services. The simulation results show that the proposed incremental learning strategy improves the classification accuracy of the proposed hybrid classifier compared to existing traditional learning methods. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.comcom.2019.11.017 | Computer Communications |
Keywords | Field | DocType |
Network traffic classification,Distributed denial of service attack,Supervised and unsupervised classification techniques,Machine learning techniques | Traffic classification,Botnet,Computer science,Incremental learning,Connectionless communication,Computer network,Resource allocation,File transfer,Classifier (linguistics),Voice over IP | Journal |
Volume | ISSN | Citations |
150 | 0140-3664 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
V. Punitha | 1 | 2 | 1.41 |
C. Mala | 2 | 25 | 9.19 |