Airborne Network Traffic Identification Method under Small Training Samples

小训练样本条件下的机载网络流量识别方法

¹ School of Information and Navigation, PLA Air Force Engineering University, Xi'an 710077, China
² School of Cybersecurity, Northwestern Polytechnical University, Xi'an 710072, China

Received: 20 November 2019

Abstract

Due to the high cost and difficulty of traffic data set acquisition and the high time sensitivity of traffic distribution, the machine learning-based traffic identification method is difficult to be applied in airborne network environment. Aiming at this problem, a method for airborne network traffic identification based on the convolutional neural network under small traffic samples is proposed. Firstly, the pre-training of the initial model for the convolutional neural network is implemented based on the complete data set in source domain, and then the retraining of the convolutional neural network is realized through the layer frozen based fine-tuning learning algorithm of convolutional neural network on the incomplete dataset in target domain, and the convolutional neural network model based feature representing transferring(FRT-CNN) is constructed to realize online traffic identification. The experiment results on the actual airborne network traffic dataset show that the proposed method can guarantee the accuracy of traffic identification under limited traffic samples, and the classification performance is significantly improved comparing with the existing small-sample learning methods.

摘要

机载网络环境下，流量数据集获取成本高、难度大，且流量分布时间敏感度较高，导致基于机器学习的流量识别方法难以获得实际应用。针对该问题，提出了一种基于卷积神经网络的小流量样本条件下机载网络流量识别方法，首先基于源领域完备数据集实现卷积神经网络初始模型的预训练，然后在目标领域数据集上，通过基于层冻结的卷积神经网络微调学习算法实现卷积神经网络的重训练，从而构造基于特征迁移的卷积神经网络（FRT-CNN）模型实现流量样本的线上分类。通过在实际机载网络流量数据集上的实验结果表明，所提方法可以在流量训练样本有限的条件下保证流量识别准确性，且分类性能相比于现有小样本学习方法有显著提升。