摘要
随着网络攻击手段持续演进,新型攻击方式层出不穷。为此,提出基于深度强化学习的网络流量数据异常辨识方法。该方法利用深度强化学习算法实时监测网络流量,采用Softmax分类模型划分监测数据类别,通过设定阈值实现对网络流量数据的异常辨识。实验结果表明,设计方法不仅可以实现对网络流量中异常数据的划分与聚类,还具有较高的准确率。
With the continuous evolution of network attack methods,new types of attack methods emerge one after another.Therefore,a network traffic data anomaly identification method based on deep reinforcement learning is proposed.This method utilizes deep reinforcement learning algorithms to monitor network traffic in real-time,divides monitoring data categories using a Softmax classification model,and identifies anomalies in network traffic data by setting thresholds.The experimental results show that the design method can not only achieve the division and clustering of abnormal data in network traffic,but also has high accuracy.
作者
程文渊
CHENG Wenyuan(Zhongdian Taiji(Group)Co.,Ltd.,Beijing 100083,China)
出处
《智能物联技术》
2025年第4期87-91,共5页
Technology of Io T& AI
关键词
深度强化学习
网络流量监测
异常分类
辨识方法
数据异常
网络流量
deep reinforcement learning
network traffic monitoring
abnormal classification
identification method
data abnormality
network flow
