基于SIR模型的隐蔽信道数据安全检测仿真

隐蔽信道数据分布散乱,对数据检测造成阻碍。针对传统的隐蔽信道数据检测方法存在检测速度慢、有效性差等问题,提出一种基于SIR模型的隐蔽信道数据安全检测方法。构建SIR隐蔽信道模型,使用在线检测模型进行隐蔽信道数据编码处理,使用密度聚类算法对隐蔽信道编码数据进行搜索聚类,划分密度区域,通过判断各密度区域数据有效性,完成隐蔽信道数据的密度聚类。利用决策树对聚类完成的数据进行特征属性提取,引入特征属性获取新的信息递增率,通过数据间差异性计算完成隐蔽信道数据安全检测。实验结果表明,所提方法能有效完成隐蔽信道数据检测,精准度、效率和稳定性均优于传统方法,且检测耗时少,具有显著优势。

Simulation of Covert Channel Data Security Detection Based on SIR Model

Traditionally, hidden channel data distribution is scattered and it hinders the data detection. In order to solve the problems of the slow detection and poor effectiveness in the traditional hidden channel data detection methods, a new detection method of the hidden channel data based on SIR model was proposed. Firstly, the SIR hidden channel model was built, and the online detection model was used to encode the hidden channel data. Secondly, the density clustering algorithm was used to search for the coded hidden channel data, so as to divide the density region. Thirdly, the density clustering of hidden channel data was completed by judging the effectiveness of data in each density region. Moreover, the decision tree was used to extract the feature attributes of the clustered data, and the feature attributes were introduced to obtain the new increment rate. Simulation results show that the proposed method can effectively detect the hidden channel data, which has better accuracy, efficiency and stability than the traditional method. Meanwhile, the proposed method has less detection time.