计算机科学 ›› 2016, Vol. 43 ›› Issue (9): 57-60.doi: 10.11896/j.issn.1002-137X.2016.09.010
• 2015 年第三届CCF 大数据学术会议 • 上一篇 下一篇
马钲然,张博锋,王勇军
MA Zheng-ran, ZHANG Bo-feng and WANG Yong-jun
摘要： 提出了一种新的用于学习和分辨网络异常行为的方法。与之前的工作相比,将采用主题模型对网络异常行为进行建模并构建分类器。根据连接的分类标签,在训练模型之前将数据集分成两部分,即正常的部分和异常的部分。通过分析模型参数对结果的影响可以发现α(主题的狄利克雷参数)和主题数量对于预测结果具有正相关性,而β(特征号的狄利克雷参数)对于预测结果具有负相关性。通过KDDCUP’99数据集对该模型进行评估,结果显示预测的准确度达到91.69%,比SVM等算法在正常和异常行为分类上的表现更好。
| [1] Garcia-Teodoro P,Diaz-Verdejo J,Macia-Fernandez G,et al.Anomaly-based network intrusion detection:Techniques,systems and challenges[J].Computers & Security,2009,28(1/2):18-28 [2] Blei D M,Ng A Y,Jordan M I.Latent dirichlet allocation[J].J.Mach.Learn.Res.,2003,3:993-1022 [3] Blei D M.Probabilistic topic models[J].Commun.ACM,2012,55(4):77-84 [4] Fei-Fei L,Perona P.A bayesian hierarchical model for learning natural scene categories[C]∥IEEE Computer Society Confe-rence on Computer Vision and Pattern Recognition,2005(CVPR 2005).IEEE,2005,2:524-531 [5] Cramer,Christopher,Carin L.Bayesian topic models for describing computer network behaviors[C]∥2011 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).IEEE,2011:1888-1891 [6] Newton B D.Anomaly Detection in Network Traffic Traces Using Latent Dirichlet Allocation.http://www.cs.unc.edu/~bn/BenNetwonFinalProjectReport.pdf [7] Huang J,Kalbarczyk Z,Nicol D M.Knowledge Discovery from Big Data for Intrusion Detection Using LDA[C]∥2014 IEEE International Congress on Big Data (BigData Congress).IEEE,2014:760-761 [8] Kasliwal B,Bhatia S,Saini S,et al.A hybrid anomaly detection model using G-LDA[C]∥2014 IEEE International Advance Computing Conference (IACC).IEEE,2014:288-293 [9] http://kdd.ics.uci.edu/databases/kddcup 99/kddcup99.html |
| No related articles found! |
|
||
首页