2019年研究生学术前沿讲座(48)-An Intrusion Detection Approach Based on Improved Deep Belief Network

2019年研究生学术前沿讲座(48

 

人:李冠憬  教授  加州大学欧文分校

主题名称:An Intrusion Detection Approach Based on Improved Deep Belief Network

内容简介:

With the advances and development of network technology, network attacks and intrusion methods have become increasingly complex and diverse. At present, these existing intrusion detection technologies have overfitting, low classification accuracy and high false positive rate (FPR). In this paper, an intrusion detection approach based on improved Deep Belief Network (DBN) is proposed, where the dataset is processed by Probabilistic Mass Function (PMF) encoding and Min-Max normalization method to simplify the data preprocessing. And, a combined sparse penalty term based on Kullback-Leibler (KL) divergence and non-mean Gaussian distribution is introduced in the likelihood function of the unsupervised training phase of DBN. The sparse distribution of the dataset is obtained by sparse constraints, avoiding the problem of feature homogeneity and overfitting. By using the NSL-KDD and UNSW-NB15 datasets, the experimental results show that the proposed approach has significant improvement in classification accuracy, and FPR.

时间地点:20191026日,信息235

主办学院:信息工程学院

 

  

365足球外围平台

2019.10.17

分类: 
  • 分类:
    培养工作
Baidu
sogou