论文部分内容阅读
针对入侵检测系统的高漏报率及高误报率问题,提出一种混杂入侵检测模型。该模型分别构造基于核主成分分析(KPCA)和核独立成分分析(KICA)的特征提取器,并采用集成学习对特征提取结果进行整合学习。采用分布式神经网络对集成结果进行再学习,从而实现对大规模数据的分布式处理。通过反馈机制调节KPCA和KICA的集成学习权重,达到最优检测效果。采用KDD CUP’99数据集进行测试实验,结果表明:该模型能够获得较高的检测正确率,同时具有较低的漏报率及误报率。
Aiming at the problem of high false negative rate and high false negative rate of intrusion detection system, a hybrid intrusion detection model is proposed. The model constructs a feature extractor based on kernel principal component analysis (KPCA) and kernel independent component analysis (KICA), respectively, and adopts integrated learning to integrate the results of feature extraction. Using distributed neural network to re-learn the integration results, so as to realize the distributed processing of large-scale data. Through the feedback mechanism to adjust the KPCA and KICA integrated learning weights, to achieve the best detection results. The KDD CUP’99 dataset was used to test the model. The experimental results show that the model can achieve high detection accuracy, low false alarm rate and false positive rate.