基于多约束信息融合的特定网络检测方法设计

针对当前特定网络检测方法中没有对数据粒度进行过滤,数据粒度过于粗糙,检测过程的单一,致使检测效率低、检测正确性偏差等问题。提出一种基于多约束信息融合的特定网络检测方法,利用Windows中的Wpcap.dll获取特定网络中NIC相关信息,构建特定网络侦听,制定过滤条件实现特定网络数据的获取；根据Rough集理论对特定网络数据粒度进行过滤,减小数据粒度的粗糙程度；构建特定网络检测模型,结合D-S证据理论得到基本置信函数值并确定值的权重,代入D-S合成公式获得检测结果,引入群体信任法对检测结果再次过滤,实现网络异常数据的彻底检测和清除,解决检测方法的单一性。实验表明,该方法提高了网络检测的效率和正确性,有效解决了当前网络检测方法中存在的问题。

Design of Specific Network Detection Method Based on Multi - Constrained Information Fusion

In view of the current specific network detection method, there is no data granularity filtering, the data granularity is too rough, the detection process is single, resulting in low detection efficiency, detection correctness deviation and other issues. Put forward a specific network detection method for multi constraints based on information fusion, to obtain the specific network NIC information using Windows Wpcap.dll in the construction of a specific network interception, making filtering conditions to achieve access to specific network data; according to the theory of Rough sets of specific network data filtering granularity, reduce the roughness of the construction of a specific data granularity; the network detection model, combined with D-S evidence theory are basic belief function value and determine the value of weight by D-S synthesis formula get the test results, the introduction of group trust method filtered again on the test results, the complete network anomaly detection data and clear, single solution detection method. The experiment shows that this method improves the efficiency and correctness of network detection, and effectively solves the problems existing in the current network detection methods.