摘要
入侵检测系统在发现网络异常、确保电力系统网络安全方面发挥着重要作用。电力流量具有数据流向固定、查全率要求高、时序性强等特点,为解决一般检测方法计算复杂度高、准确率低的问题,提出一种基于EfficientNet的高效用电力入侵检测方法。该方法首先对电力流量数据进行预处理与数据转换;然后利用高效用模型EfficientNet提取输入电力数据中的帧级网络攻击特征;最后将提取的图像级特征表示映射到分类空间,并利用全连层网络以及softmax进行分类并输出检测结果,实现电力数据的网络入侵检测。实验结果表明,该方法能够在保持较高分类精度的同时有效减少模型参数量、降低模型复杂度,提高了异常流量入侵检测效率。
Intrusion detection systems play an important role in detecting network anomalies and ensuring network security in the power sys⁃tem.Power flow has the characteristics of fixed data flow direction,high recall requirements,and strong timing.To solve the problems of high computational complexity and low accuracy in general detection methods,an efficient power intrusion detection method based on EfficientNet is proposed.This method first preprocesses and converts power flow data;Then,efficient model EfficientNet is used to extract frame level net⁃work attack features from input power data;Finally,the extracted image level feature representations are mapped to the classification space,and a fully connected layer network and softmax are used to classify and output detection results,achieving network intrusion detection of pow⁃er data.The experimental results show that this method can effectively reduce the number of model parameters,reduce model complexity,and improve the efficiency of anomaly traffic intrusion detection while maintaining high classification accuracy.
作者
张章学
ZHANG Zhangxue(Fujian Strait Information Technology Co,.Ltd.,Fuzhou 350003,China)
出处
《软件导刊》
2023年第10期139-145,共7页
Software Guide
基金
中央引导地方科技发展专项(2021L3032)。
关键词
神经网络
电力流量
入侵检测
neural network
electricity flow
intrusion detection
