作者: Mohamed Nassar , Radu State , Olivier Festor
DOI: 10.1007/978-3-540-87403-4_17
关键词:
摘要: We propose a novel online monitoring approach to distinguish between attacks and normal activity in SIP-based Voice over IP environments. demonstrate the efficiency of even when only limited data sets are used learning phase. The solution builds on set 38 features VoIP flows uses Support Vector Machines for classification. validate our proposal through large offline experiments performed mix real world traces from provider locally generated own testbed. Results show high accuracy detecting SPIT flooding promising performance an deployment measured.