基于贝叶斯网络的公安网络执法手段研究
|
摘要
公安传统网络执法手段难以应对日益复杂的网络,急需探索高效灵活的新途径。贝叶斯网络作为机器学习中重要的算法,被广泛应用于人工智能领域。然而,公安网络执法中尚未有相应的应用。论文提出一种新型的贝叶斯网络进行文本感情分析的方法,实现高效率的自动化网络舆情监控,并由此实现了基于犯罪目标求解一条最优的"侦查、渗透、取证"网络执法流程,完成自动化网络犯罪打击。此外,动态贝叶斯网络能够不断根据前驱训练结果和外部因素进行反馈调整,相比静态传统手段在精度和灵活性上都更加契合公安工作的需求。
The traditional law enforcement means of public security is difficult to deal with the increasingly complicated network, so it is urgent to explore a new way of efficient and flexible. As an important algorithm in machine learning, Bayesian network is widely used in the field of artificial intelligence.However, there is no corresponding application in police network law enforcement. In this paper, a new Bayesian network for text affective analysis is proposed, which realizes an efficient automatic network monitoring of public opinion, and thus realizes an optimal "investigation, infiltration, forensics" Network law enforcement process based on the crime target to complete the automatic cybercrime attack. In addition, the dynamic Bayesian network can continuously adjust the feedback according to the result of the precursor training and external factors, which is more consistent with the demand of the public security work than the static traditional method in accuracy and flexibility.
The traditional law enforcement means of public security is difficult to deal with the increasingly complicated network, so it is urgent to explore a new way of efficient and flexible. As an important algorithm in machine learning, Bayesian network is widely used in the field of artificial intelligence.However, there is no corresponding application in police network law enforcement. In this paper, a new Bayesian network for text affective analysis is proposed, which realizes an efficient automatic network monitoring of public opinion, and thus realizes an optimal "investigation, infiltration, forensics" Network law enforcement process based on the crime target to complete the automatic cybercrime attack. In addition, the dynamic Bayesian network can continuously adjust the feedback according to the result of the precursor training and external factors, which is more consistent with the demand of the public security work than the static traditional method in accuracy and flexibility.
引文
[1](美)James Broad,Andrew Bindner.Kali渗透测试技术实战[M].北京:机械工业出版社,2014(9):P3.
[2]吴军.数学之美(第二版)[M].北京:人民邮电出版社,2014(11):P214-P215.
[3]魔术.Metasploit自动攻击和选择模块攻击详解[J].www.freebuf.com/articles/web/5628.htm,2012(9).
[4]刘涛.机器学习算法在校园网入侵检测系统中的应用[J].黑河学院学报,2017(9):P215-P216.
[5]刘兰,林军,蔡君.面向大数据的异构网络安全监控及关联算法研究[J].电信科学,2014(7):P84-86.
[6]王聪,张仁斌,李钢.基于关联特征的贝叶斯Android恶意程序检测技术[J].计算机应用与软件,2017(1):P286-P287.
[7]胡浩,叶润国,张红旗,杨英杰,刘玉岭.基于攻击预测的网络安全态势量化方法[J].通信学报,2017(10):P122-P124.
[8]宫泽林,徐艳红.创新大数据技术下网络舆情监测与分析的研究[J].网络空间安全,2016(6):P4.
[9]章翔凌,杨永群,黄勤龙,陈权.基于大数据分析的应用安全态势系统设计与实现[J].网络空间安全,2017(2-3):P56-P57.
[10]弋建伟,马晓荣.基于Java的维基利亚密码分析[J].陕西师范大学学报(自然科学版),2008(36):P9-P10.
[2]吴军.数学之美(第二版)[M].北京:人民邮电出版社,2014(11):P214-P215.
[3]魔术.Metasploit自动攻击和选择模块攻击详解[J].www.freebuf.com/articles/web/5628.htm,2012(9).
[4]刘涛.机器学习算法在校园网入侵检测系统中的应用[J].黑河学院学报,2017(9):P215-P216.
[5]刘兰,林军,蔡君.面向大数据的异构网络安全监控及关联算法研究[J].电信科学,2014(7):P84-86.
[6]王聪,张仁斌,李钢.基于关联特征的贝叶斯Android恶意程序检测技术[J].计算机应用与软件,2017(1):P286-P287.
[7]胡浩,叶润国,张红旗,杨英杰,刘玉岭.基于攻击预测的网络安全态势量化方法[J].通信学报,2017(10):P122-P124.
[8]宫泽林,徐艳红.创新大数据技术下网络舆情监测与分析的研究[J].网络空间安全,2016(6):P4.
[9]章翔凌,杨永群,黄勤龙,陈权.基于大数据分析的应用安全态势系统设计与实现[J].网络空间安全,2017(2-3):P56-P57.
[10]弋建伟,马晓荣.基于Java的维基利亚密码分析[J].陕西师范大学学报(自然科学版),2008(36):P9-P10.