作者: Vadiraj Panchamukhi , Hema A. Murthy
关键词:
摘要: An anomaly is an activity that deviates from the wellknown behaviour of system. Anomaly detection in networks interest two perspectives: organization's perspective and Internet Service Provider's (ISP) perspective. Protection its computer network infrastructure important task for all organizations. Organizations desire their are robust resilient to any kind attack. forms part this resiliency. Also ISPs want maximize utilization resources. Hence ISP would be interested know resource failure immediately so as correct problem. also safeguarding malicious activities. We describe here a Gaussian Mixture Model (GMM)-based traffic verification system paradigm detection. The characteristics aggregated over period time given model verify validity traffic. If does not obey then we raise alarm flagging it anomaly. Our results show performs with less than 1% misses false alarms.