基于AHP-CNN的加密流量分类方法
Encryption Traffic Classification Method Based on AHP-CNN
游嘉靖 1何月顺 2何璘琳 2钟海龙1
作者信息
- 1. 东华理工大学信息工程学院,江西 南昌 330013;江西省网络空间安全智能感知重点实验室,江西 南昌 330013
- 2. 东华理工大学信息工程学院,江西 南昌 330013
- 折叠
摘要
为了解决现有方法在加密流量特征提取方面不够充分的问题,本文提出一种基于自注意力混合池化卷积神经网络(Attention-based Hybrid Pooling Convolutional Neural Network,AHP-CNN)的加密流量分类方法.该方法对卷积神经网络(Convolutional Neural Network,CNN)的池化层进行改进,以并联形式将平均池化层和最大池化层相结合,形成双层同步池化的模式,从而实现对网络加密流量整体特征和局部特征的捕捉.再将自注意力模块嵌入到模型中,增强模型对于加密流量特征依赖关系的提取,从而更加精准地对加密流量进行分类.实验结果表明,本文所提出的网络模型在识别加密流量的准确率方面有着显著提升,并且F1分数达到了0.94以上.本文为网络加密流量分类提供了一种更为有效且精确的方法,有助于提升网络安全领域的研究与应用能力.
Abstract
To address the insufficient feature extraction of existing methods for encrypted traffic,this study proposes an en-crypted traffic classification method based on an Attention-based Hybrid Pooling Convolutional Neural Network(AHP-CNN).This method improves the pooling layers of Convolutional Neural Networks(CNNs)by combining average pooling and max pool-ing in a parallel manner,forming a dual-layer synchronized pooling pattern.This enables the capturing of both global and local features of network encrypted traffic.Furthermore,a self-attention module is incorporated into the model to enhance the extrac-tion of dependency relationships among encrypted traffic features,leading to more accurate classification.Experimental results demonstrate a significant improvement in the accuracy of encrypted traffic identification using the proposed model,with an F1 score exceeding 0.94.This research provides a more effective and precise approach for the classification of network encrypted traf-fic,contributing to advancements in research and applications in the field of network security.
关键词
深度学习/加密流量分类/卷积神经网络/混合池化/自注意力机制Key words
deep learning/encrypted traffic classification/convolutional neural network/hybrid pooling/self-attention mechanism引用本文复制引用
基金项目
江西省重点研发项目(GJJ2200729)
江西省网络空间安全智能感知重点实验室开放基金资助项目(JKLGIP202206)
出版年
2024
国家科技期刊平台
NSTL
万方数据