DAE encrypted traffic identification based on LSTM
闫金蓥 1王海珍1
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 齐齐哈尔大学 计算机与控制工程学院,黑龙江 齐齐哈尔 161006
折叠
摘要
随着虚拟专用网(VPN)技术的广泛应用,实时VPN流量识别已成为网络管理和安全维护中越来越重要的任务.加密流量使得从原始流量中提取特征变得极具挑战性,现有的VPN流量识别方法通常存在高维数据特征提取困难的问题.提出了一种在DAE(Denoising Auto-Encoder,降噪自编码器)的网络结构基础上加入了LSTM(Long Short Term Memory,长短时记忆)的模型,将深度学习相关技术融入加密流量识别技术之中,使一直存在的难以处理高维数据以及特征提取等问题得到解决.
Abstract
With the widespread application of virtual private network(VPN)technology,real-time VPN traffic identification has become an increasingly important task in network management and security maintenance.Encrypting traffic makes it highly challenging to extract features from the original traffic,and existing VPN traffic identification methods often face difficulties in high-dimensional data feature extraction.It was proposed of a model based on the network structure of denoising auto-encoder(DAE)with the addition of long short term memory(LSTM).Integrating deep learning techniques into encrypted traffic identification technology enables solutions to long-standing issues such as handling high-dimensional data and feature extraction.
关键词
降噪自编码器/加密流量识别/长短时记忆网络
Key words
denoising auto-encoder/encrypted traffic identification/long short term memory network
维普
万方数据