大数据信息传输中恶意攻击数据识别仿真

发布时间：2018-05-24 03:13

本文选题：信息传输 + 恶意攻击　；参考：《计算机仿真》2017年10期

【摘要】：大数据信息传输下恶意攻击数据的识别,能够有效提升网络数据安全稳定性。对恶意攻击数据的识别,需要对数据恶意攻击信息进行预处理,获得恶意攻击数据特征的分离过程,完成数据识别。传统方法采用定量递归分析原理分析恶意攻击数据的聚类特征,但忽略了获得恶意攻击数据特征的分离过程,导致识别精度较低。提出基于离散小波变换的恶意攻击数据识别方法。上述方法首先采用函数极值法确定隶属度,获取数据恶意攻击特征,采用离散小波变换方法对大数据信息传输中数据恶意攻击信息进行预处理,结合FIR滤波器进行网络数据抗干扰滤波处理,采用高阶累积量后置路径搜索获得大数据信息传输中恶意攻击数据特征的分离过程,实现恶意攻击数据特征的准确识别。实验结果表明,所提方法进行恶意攻击数据识别的准确度较高,抗干扰能力较强。
[Abstract]:The identification of malicious attack data under big data information transmission can effectively improve the security and stability of network data. To identify the malicious attack data, it is necessary to preprocess the malicious attack information, to obtain the separation process of the malicious attack data characteristics, and to complete the data recognition. The traditional method uses the principle of quantitative recursive analysis to analyze the clustering features of malicious attack data, but neglects the separation process of obtaining malicious attack data features, resulting in low recognition accuracy. A method of malicious attack data recognition based on discrete wavelet transform (DWT) is proposed. Firstly, the membership degree is determined by the function extremum method, and the malicious attack characteristics of data are obtained. The data malicious attack information in big data information transmission is preprocessed by discrete wavelet transform method. Combining FIR filter with network data anti-interference filtering, the separation process of malicious attack data features in big data information transmission is obtained by using high-order cumulant post-path search to realize accurate recognition of malicious attack data features. The experimental results show that the proposed method has high accuracy and strong anti-jamming ability for malicious attack data recognition.
【作者单位】：内蒙古农业大学计算机与信息工程学院;
【基金】：内蒙古农业大学基础学科科研启动基金项目(JC2015009)
【分类号】：TP393.08

【相似文献】