多维网络信息流量式泄露高效检测方法仿真

Simulation of Multi-Dimensional Network Information Flow Leak Detection Method with High Efficiency

由于多维网络平台存在异常网络流量检测准确度不高,实时性较差等问题,导致多维网络平台中用户的隐私信息泄露,网络信息安全难以维护。为此提出一种多维网络信息流量式泄露高效检测方法。通过分析网络流量系统结构,利用协议特征库对网络流量实施控制。运用归一化排除不相关以及冗余的网络流量特征,降低原始特征集的维度。根据流量式泄露网络数据信息特征构建出相空间模型,通过克隆体和匹配度之间的相关性,对抗体实施变异处理,获取泄露数据平衡特征,通过线性回归函数映射到相对应的相空间内。利用拉格朗日乘子获取最佳空间优化结果,完成多维网络信息流量式泄露的检测。仿真结果表明,所提方法有效提高了检测的准确度,降低运算时的复杂程度,具有高效性、实时性以及优质的鲁棒性。

The multi-dimensional network platform has the problems of low detection accuracy and poor real-time performance of detecting abnormal network flow. It is difficult to keep privacy information in the multi-dimensional network platform from revealing. Therefore, an efficient method of multi-dimensional network information flow-measurement-type leakage detection was proposed. By analyzing the structure of network flow system, we used the protocol feature base to control the network traffic. In order to reduce the dimension of original feature set, we used the normalization to eliminate irrelevant and redundant network traffic features. According to the information features of flow-measurement-type leakage network data, we built a phase space model. Through the correlation between clones and matching degree, we mutated the antibody, so as to obtain the balance characteristics of leaked data, which was mapped to the corresponding phase space by linear regression functions. Finally, we used Lagrange multiplier to obtain the best result of space optimization, and thus to complete the detection for multi-dimensional network information flow-measurement-type leakage. Simulation results prove that the proposed method effectively improves the accuracy of detection and reduces the complexity of operation. In addition, this method has high efficiency, real-time performance and high-quality robustness.