|Performance Analysis of Semi-Supervised Machine Learning Approach for DDoS Detection|
|Mehnaz Anjum, Dr. Shreedhara K S|
|Cite This Article:|
Performance Analysis of Semi-Supervised Machine Learning Approach for DDoS Detection, International Journal of Innovative Research in Technology(www.ijirt.org) ,ISSN: 2349-6002 ,Volume 6 ,Issue 2 ,Page(s):144-147 ,July 2019 ,Available :IJIRT148476_PAPER.pdf
|Semi-Supervised, Clustering, Random forest.|
|DDoS – Distributed daniel of service is one of the cyber-attack, which remains as a major attack on internet for past many years. DDoS detection based on Machine Learning techniques such as, Supervised and Unsupervised techniques has been already implemented which has some drawbacks like low detection accuracy and high false positive rates. In this paper, DDoS detection based on Semi-Supervised Machine learning technique is presented which is the combination of both supervised and unsupervised techniques that provides better results compared to the existing approaches. Unsupervised part consists of some estimation steps including clustering which reduces the false positive rates and increases the accuracy by reducing irrelevant data. In supervised part Random forest algorithm is used to accurately classify the DDoS attack data and it also reduces the false positive rate of unsupervised part.|
|Unique Paper ID: 148476|
Publication Volume & Issue: Volume 6, Issue 2
Page(s): 144 - 147
|Article Preview & Download|
Energy and Spectral Efficiency of Cellular Network...
Paper ID : IJIRT148815
MULTI-ANTENNA WIRELESS LEGITIMATE SURVEILLANCE SYS...
Paper ID : IJIRT148814
DESIGN OF PILOT SEQUENCE BASED PREAMBLE FOR FBMC F...
Paper ID : IJIRT148811
DESIGN OF LOW-COMPLEXITY BLIND CFO ESTIMATION FOR ...
Paper ID : IJIRT148810
RESOURCE ALLOCATION STRATEGY FOR MULTI-USER COGNIT...
Paper ID : IJIRT148809