CAJ | 학술논문

研究了入侵检测系统中海量数据分类的问题．讨论了深度信念网络（DBN）的原理，提出了基于 DBN的入侵检测模型．DBN 由多层无监督的限制玻尔兹曼机（RBM）网络和一层有监督的反向传播（BP）网络构成．该入侵检测模型采用一种快速、贪婪的方法对 DBN 网络进行预训练，利用对比分歧算法逐层训练每一个 RBM 网络；然后，利用有监督的 BP 算法对整个 DBN 网络进行微调，并同时对 RBM 网络输出的低维特征进行入侵数据分类．基于 KDD CUP 1999数据集的实验结果表明，使用3层以上的 DBN 模型分类效果优于自组织映射和神经网络方法．因此，DBN 是一种有效且适用于高维特征空间的入侵检测方法．
연구료입침검측계통중해량수거분류적문제．토론료심도신념망락（DBN）적원리，제출료기우 DBN적입침검측모형．DBN 유다층무감독적한제파이자만궤（RBM）망락화일층유감독적반향전파（BP）망락구성．해입침검측모형채용일충쾌속、탐람적방법대 DBN 망락진행예훈련，이용대비분기산법축층훈련매일개 RBM 망락；연후，이용유감독적 BP 산법대정개 DBN 망락진행미조，병동시대 RBM 망락수출적저유특정진행입침수거분류．기우 KDD CUP 1999수거집적실험결과표명，사용3층이상적 DBN 모형분류효과우우자조직영사화신경망락방법．인차，DBN 시일충유효차괄용우고유특정공간적입침검측방법．
This paper focuses on the intrusion classification of huge amounts of data in a network intrusion detection system. An intrusion detection model based on deep belief nets (DBN) is proposed to conduct intrusion detection,and the principles regarding DBN are discussed.The DBN is composed of a multiple unsupervised restricted Boltzmann machine (RBM) and a supervised back propagation (BP)network.First,the DBN in the proposed model is pre-trained in a fast and greedy way,and each RBM is trained by the contrastive divergence algorithm.Secondly,the whole network is fine-tuned by the supervised BP algorithm,which is employed for classifying the low-dimensional features of the intrusion data generated by the last RBM layer simultaneously.The experimental results on the KDD CUP 1999 dataset demonstrate that the DBN using the RBM network with three or more layers outperforms the self-organizing maps (SOM)and neural network (NN)in intrusion classification.Therefore,the DBN is an efficient approach for intrusion detection in high-dimensional space.