利用网络望远镜和LSTM神经网络的大数据环境网络异常探测模型  

Network Anomaly Detection Model in Big Data Environment Using Network Telescope and LSTM Neural Network

作　　者：邓小亚 DENG Xiaoya(School of Intelligent Manufacturing,Sichuan University of Arts and Science,Dazhou,Sichuan 635000,China)

机构地区：[1]四川文理学院智能制造学院,四川达州635000

出　　处：《计算技术与自动化》2024年第3期159-166,共8页Computing Technology and Automation

基　　金：政务数据安全达州市重点实验室资助项目(ZSAQ202204,ZSAQ202201);智能制造产业技术研究院资助项目(ZNZZ202212)。

摘　　要：在当前大数据环境下,保障网络安全与稳定对于维护网络健康至关重要,而网络异常的及时探测则显得尤为迫切。为此,提出了一种基于网络望远镜技术和长短时记忆神经网络(LSTM)的网络异常探测模型。通过对中国某地区近期捕获的互联网流量进行实验验证,结果显示本文方法在不同程度的网络攻击检测中均表现出良好的性能。In the current era of big data,ensuring network security and stability is of paramount importance for maintaining the overall health of networks.Prompt detection of network anomalies has become particularly urgent.To address this,a network anomaly detection model based on the combination of network telescope technology and long short-term memory(LSTM)neural networks is proposed.Through the experimental validation on recent captured Internet traffic in a specific region of China,the results demonstrate the efficacy of the proposed method in detecting network attacks of varying degrees.

关 键 词：网络异常 异常检测 网络望远镜 深度网络 大数据 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]