基于SimHash与神经网络的网络异常检测方法研究
|
摘要
计算机网络在给人们带来极大便利的同时也存在着各种攻击隐患,因此需要完善的异常检测系统消除这些隐患。针对传统的网络异常检测方法检测效率低下、检测率较低的问题,该文在深度神经网络的基础上通过添加Simhash数据处理的方法构建了一种新的网络异常检测模型。实验结果表明,相较于传统的模型,新模型在保持神经网络使用相同长度输入的条件下获得更高的检测率。
Computer network brings great convenience to people,but there are also various hidden dangers of attacks.Therefore,a perfect anomaly detection system is needed to eliminate these hidden dangers.Aiming at the problem of low efficiency and low detection rate of traditional network anomaly detection methods,a new network anomaly detection model is constructed by adding Simhash data processing method on the basis of deep neural network.The experimental results show that compared with the traditional model,the new model achieves higher detection rate while maintaining the same length input of the neural network.
Computer network brings great convenience to people,but there are also various hidden dangers of attacks.Therefore,a perfect anomaly detection system is needed to eliminate these hidden dangers.Aiming at the problem of low efficiency and low detection rate of traditional network anomaly detection methods,a new network anomaly detection model is constructed by adding Simhash data processing method on the basis of deep neural network.The experimental results show that compared with the traditional model,the new model achieves higher detection rate while maintaining the same length input of the neural network.
引文
[1] Manku G S, Jain A, Das Sarma A. Detecting Near-duplicatesfor Web Crawling[C]//Proceedings of the 16th InternationalConference on World Wide Web. ACM,2007:141-149.
[2]王岩.卷积神经网络在肝穿刺图像分类中的应用[J].电脑知识与技术,2018,14(25):203-205.
[3]杨洋,汪毓铎.基于改进卷积神经网络算法的语音识别[J].应用声学,2018,37(06):940-946.
[4] Vinayakumar R, Soman K P, Poornachandran P. Applying con-volutional neural network for network intrusion detection[C]//2017 International Conference on Advances in Computing,Communications and Informatics(ICACCI). IEEE, 2017:1222-1228.
[5]刘月峰,王成,张亚斌,苑江浩.面向网络入侵检测系统的深度卷积神经网络模型[J].内蒙古科技大学学报,2018,37(01):59-64.
[6]杨丽,吴雨茜,王俊丽,刘义理.循环神经网络研究综述[J].计算机应用,2018,38(S2):1-6+26.
[7]胡荣磊,芮璐,齐筱,等.基于循环神经网络和注意力模型的文本情感分析[J/OL].计算机应用研究,2019,36(11).[2018-08-10]. http://www.arocmag.com/article/02-2019-11-025.html.
[8] Wang W, Sheng Y, Wang J, et al. HAST-IDS:Learning Hi-erarchical Spatial-Temporal Features using Deep Neural Net-works to Improve Intrusion Detection[J]. IEEE Access, 2017:1-1.
[9] Shiravi A, Shiravi H, Tavallaee M, et al. Toward developinga systematic approach to generate benchmark datasets for in-trusion detection[J]. Computers&Security, 2012, 31(3):357-374.
[2]王岩.卷积神经网络在肝穿刺图像分类中的应用[J].电脑知识与技术,2018,14(25):203-205.
[3]杨洋,汪毓铎.基于改进卷积神经网络算法的语音识别[J].应用声学,2018,37(06):940-946.
[4] Vinayakumar R, Soman K P, Poornachandran P. Applying con-volutional neural network for network intrusion detection[C]//2017 International Conference on Advances in Computing,Communications and Informatics(ICACCI). IEEE, 2017:1222-1228.
[5]刘月峰,王成,张亚斌,苑江浩.面向网络入侵检测系统的深度卷积神经网络模型[J].内蒙古科技大学学报,2018,37(01):59-64.
[6]杨丽,吴雨茜,王俊丽,刘义理.循环神经网络研究综述[J].计算机应用,2018,38(S2):1-6+26.
[7]胡荣磊,芮璐,齐筱,等.基于循环神经网络和注意力模型的文本情感分析[J/OL].计算机应用研究,2019,36(11).[2018-08-10]. http://www.arocmag.com/article/02-2019-11-025.html.
[8] Wang W, Sheng Y, Wang J, et al. HAST-IDS:Learning Hi-erarchical Spatial-Temporal Features using Deep Neural Net-works to Improve Intrusion Detection[J]. IEEE Access, 2017:1-1.
[9] Shiravi A, Shiravi H, Tavallaee M, et al. Toward developinga systematic approach to generate benchmark datasets for in-trusion detection[J]. Computers&Security, 2012, 31(3):357-374.