基于Fisher-PCA和深度学习的入侵检测方法研究

为了在攻击形式多样化、入侵数据海量及多维化的环境中快速、准确地识别网络攻击，提出了一种融合Fisher-PCA特征提取与深度学习的入侵检测算法。通过Fisher特征选择算法选出重要的特征组成特征子集，然后基于主成分分析法（Principal Component Analysis，PCA）将特征子集进行降维，提取出了分类能力强的特征集。构建了一种新的DNN（Deep Neural Networks）深度神经网络模型对网络攻击数据和正常数据进行识别与分类。在KDD99数据集上进行试验，结果表明这种入侵检测算法与传统的ANN、SVM算法相比，在准确率上分别提高了12.63%、6.77%，在误报率上由原来的2.31%、1.96%降为0.28%，与DBN4 、PCA-CNN算法相比，在准确率和检测率保持基本相同的同时有着更低的误报率。

Intrusion Detection Method Based on Fisher-PCA and Deep Learning

In order to quickly and accurately identify network attacks in a multi-dimensional environment with diversified attack forms, massive intrusion data and multi-dimensional environment, an intrusion detection model combining Fisher-PCA feature extraction and deep learning was proposed. Firstly, the Fisher feature selection algorithm selects important features to form feature subsets, and then the feature subsets are dimensionally reduced based on Principal Component Analysis (PCA), the feature set with strong classification ability is extracted. A new Deep Neural Network (DNN) is constructed to identify and classify network attack data and normal data. The experiment results on KDD99 dataset show that compared with the traditional ANN and SVM algorithms, the accuracy of this intrusion detection algorithm is improved by 12.63% and 6.77% respectively, and the false alarm rate is reduced from 2.31% and 1.96% to 0.28%, Compared with DBN4 and PCA-CNN algorithm, the accuracy and detection rate are basically the same, while the false alarm rate is lower.