Cloud platform network intrusion detection method

The invention discloses a cloud platform network intrusion detection method, and the method comprises the steps: collecting network intrusion data, and carrying out the marking of the data, and obtaining a training set; preprocessing the data of the training set, wherein the preprocessing comprises redundant sample removal and unbalance processing; inputting the preprocessed data into a trained convolutional neural network for feature extraction; and inputting the extracted features into a classifier for binary classification to obtain a classification result. The depth feature and the time feature are obtained at the same time, the spatial feature is enhanced through the attention mechanism, the detection precision can be improved, and the method has high robustness and generalization ability. 本发明公开了一种云平台网络入侵检测方法，所述方法包括采集网络入侵数据，并对所述数据进行标注，得到训练集；对所述训练集的数据进行预处理，所述预处理包括冗余样本去除和不平衡处理；将预处理后的数据输入训练好的卷积神经网络进行特征提取；将提取的特征输入至分类器进行二分类得到分类结果。本发明同时获取深度特征及时间特征并通过注意力机制增强空间特征，能够提高检测精度，具有较高的鲁棒性和泛化能力。