基于分布式PageRank算法的可疑目标挖掘  

Suspicious target mining based on distributed PageRank algorithm

作　　者：李国玉 周广禄 张兆心 

机构地区：[1]哈尔滨工业大学(威海)网络与信息内容安全技术研究中心,威海264200

出　　处：《高技术通讯》2017年第5期410-415,共6页Chinese High Technology Letters

基　　金：国家科技支撑计划(2012BAH45B01);国家自然科学基金(61100189;61370215;61370211;61402137);国家信息安全242计划(2016A104)资助项目

摘　　要：考虑到恶意木马、病毒等通过URL传播,已对网络安全构成了重大威胁,提出了一种高效的基于分布式PageRank链接分析的可疑URL目标筛选过滤算法。该算法通过构建URL危险性计算分析模型,迭代计算目标危险值,直至收敛状态。最后,根据得到的目标的危险值筛选可疑目标。通过实验验证了该算法的有效性。实验证明,分布式PageRank链接分析适应大矩阵计算,可以有效分析挖掘可疑URL目标。Considering that Malicious Trojans, viruses and others spread through URL and this poses a major threat to network security, the study proposed an efficient algorithm for screening and filtering suspicious URL targets based on distributed PageRank link analysis. The algorithm through constructing a model for calculation and analysis of URL hazard iteratively calculates the valus of target risks, and this continues until the convergence state. Finally, it selects the suspicious target according to its dangerous value. The effectiveness of the algorithm was verified by experiment, and the experimental results show that the distributed PageRank link analysis can adapt to large matrix computation, and can effectively analyze suspicious URL targets.

关 键 词：网络安全 云计算 MAPREDUCE PAGERANK 可疑目标挖掘 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]