论文部分内容阅读
现行网络中存在诸多影响网络安全和服务性能的异常流量,异常流量的存在不仅影响用户的正常使用,而且会造成网络拥塞和网络瘫痪,甚至会篡改和破坏用户及服务器的数据,造成不可估量的损失。为及时发现这些流量,设计了一个基于自相似特性的异常流量检测模型。根据现行网络流量大速度快等特点,该模型设计分为简单流分类模块、自适应抽样模块、实时估计Hurst参数模块以及异常流量判断模块四部分。设计的此检测模型能够在很大程度上保证网络流量检测的准确性和高效性。
In the existing network, there are many abnormal traffic affecting the network security and service performance. The existence of abnormal traffic not only affects the normal use of users, but also causes network congestion and network paralysis, even tampering with and destroying user and server data, resulting in incalculable loss. In order to discover these traffic in time, an abnormal traffic detection model based on self-similar features is designed. According to the characteristics of current network traffic such as high speed, this model is divided into four parts: simple flow classification module, adaptive sampling module, real-time estimation Hurst parameter module and abnormal flow judgment module. The designed detection model can largely ensure the accuracy and efficiency of network traffic detection.