微型电脑应用

针对隐蔽性网络攻击难以防范的问题，从寻找网络攻击根源出发，设计基于双向蚁群算法的隐蔽性网络攻击识别的方案。该方案通过大数据收集绘制可疑节点的IP画像，通过IP画像确定网络攻击的源头。采用基于DBSCAN算法的黑白双分类器对异常数据进行双重分离，保证数据分类的准确性。该方案基于双向蚁群算法寻找最优路径，保证在网络攻击时可以及时切断通信线路，保证用户免受网络的隐蔽性攻击。实验表明，所设计方案在对隐蔽性网络攻击的识别方面具有较大的性能提升。

Aimed at the problem that it is difficult to prevent covert network attacks, this research starts from finding the root of network attacks, and designs a scheme for identifying covert network attacks based on bi-directional ant colony algorithm. This scheme collects big data to draw IP portraits of suspicious nodes, and determines the source of network attacks through IP portraits. A black-and-white dual classifier is designed based on DBSCAN algorithm to double separate the abnormal data to ensure the accuracy of data classification. This scheme is based on the bi-directional ant colony algorithm to find the optimal path, which can ensure that the communication line can be cut off in time when the network attacks, and ensure that users are free from covert attacks of the network. The experiment shows that the designed scheme has a greater performance improvement in the identification of covert network attacks.