Abstract: Traditional FCM algorithm is too dependent on initial distance and Euclidean distance is only applied to han- dle the dataset of numeric and spatial data structure for the super-ball. Based on fuzzy rough sets and ReliefF technolo- gy, the author proposed a fuzzy rough set based clustering algorithm(FRS-FCM) , and used it to integrated intrusion de- tection. By effective clustering and integrated learning, the algorithm can improve the detection rate and reduce the false detection rate, improve the detection rate of low-frequency attacks. Finally, simulation experiments using KDl)Cup 99 data set verify feasibility and effectiveness of the algorithm.

Key words: Fuzzy rough sets, ReliefF, FRS-FCM, Integrated intrusion detection