Imbalanced Classification Algorithm in Botnet Detection
Yun Yang, Guyu Hu, Shize Guo, Jun Luo · 2010
An Imbalanced Classification anomaly detection algorithm called “I-SVDD” for detecting Botnet was put forward in this paper. The algorithm combines the One-Class classification with the known Intrusion behaviors. This algorithm has proven effective in reducing the number of botnet clients. The true positives reaches nearly 100% and False Positive reaches 0% respectively. Hence, adjusting some parameters can make the false positive rate better. So using Imbalanced Classification method in Anomaly detection may be a future orientation in Pervasive computing area.