Dynamical class-weighted-based convolutional neural networks attack detection model

FAN Rong

doi:10.11959/j.issn.1000-0801.2025113

您当前的位置：

首页 >

文章列表页 >

Dynamical class-weighted-based convolutional neural networks attack detection model

Research and Development | 更新时间：2025-09-04

- Dynamical class-weighted-based convolutional neural networks attack detection model
- Telecommunications Science Vol. 41, Issue 8, Pages: 176-185(2025)
- 作者机构：
  
  驻马店职业技术学院，河南驻马店 463000
- 作者简介：
- 基金信息：
  
  The Key Scientific Research Project of Higher Education Institutions in Henan Province in 2021(21B880052)
- DOI：10.11959/j.issn.1000-0801.2025113
  CLC： TN929.5
- Received：06 November 2024，
  
  Revised：2025-03-21，
  
  Published：20 August 2025
- 稿件说明：
移动端阅览
樊荣.基于动态类权重的卷积神经网络攻击检测模型[J].电信科学,2025,41(08):176-185.

FAN Rong.Dynamical class-weighted-based convolutional neural networks attack detection model[J].Telecommunications Science,2025,41(08):176-185.
樊荣.基于动态类权重的卷积神经网络攻击检测模型[J].电信科学,2025,41(08):176-185. DOI： 10.11959/j.issn.1000-0801.2025113.

FAN Rong.Dynamical class-weighted-based convolutional neural networks attack detection model[J].Telecommunications Science,2025,41(08):176-185. DOI： 10.11959/j.issn.1000-0801.2025113.

摘要

入侵检测系统（intrusion detection system，IDS）作为物联网安全防御的核心组件，其性能直接影响网络的安全性。然而，入侵检测数据集中类样本的不平衡分布降低了入侵检测系统对少数类样本的检测性能。为解决这一问题，提出一种基于动态类权重的卷积神经网络的入侵检测（dynamical class-weighted-based convolutional neural network intrusion detection，DCID）模型。DCID模型采用一维卷积神经网络（1-D CNN）结构，并引入基于动态类权重的损失函数，使得DCID模型不仅能保持对多数类样本的高检测性能，也能显著提升对少数类样本的检测能力。为验证DCID模型的有效性，使用数据集CICIDS 2017进行实验。实验结果表明，与典型的机器学习模型相比，DCID模型在精确率、召回率和F1值方面表现出明显的优势。此外，还对比了不同损失函数下DCID模型的检测性能，结果表明基于动态类权重的损失函数能够有效提升少数类样本的检测性能。

Abstract

The intrusion detection system (IDS) as a core component of IoT security defense

was directly impacted in its performance

which in turn affected the overall security of the network. However

the imbalanced distribution of class samples in intrusion detection datasets is found to reduce the detection performance of IDS for minority class samples. To address this issue

a dynamical class-weighted-based convolutional neural network intrusion detection (DCID) model was proposed. The DCID model utilized a one-dimensional convolutional neural network (1-D CNN) structure and introduced a dynamical class-weighted loss function

enabling the DCID model to not only maintain high detection performance for majority class samples but also significantly enhance the detection capability for minority class samples. To validate the effectiveness of the DCID model

experiments were conducted using the CICIDS 2017 dataset. The experimental results demonstrate that

compared to typical machine learning models

the DCID model exhibites significant advantages in terms of precision

recall

and F1-score. Additionally

the detection performance of the DCID model under different loss functions was compared

and the results indicated that the dynamical class-weighted loss function effectively improved the detection performance for minority class samples.

关键词

Keywords

references

江荣旺 , 魏爽 , 龙草芳 , 等 . 基于联邦学习的车联网虚假位置攻击检测研究 [J ] . 信息安全研究 , 2023 , 9 ( 8 ): 754 - 761 .

JIANG R W , WEI S , LONG C F , et al . Research on malicious location attack detection of VANET based on federated learning [J ] . Journal of Information Security Research , 2023 , 9 ( 8 ): 754 - 761 .

林同灿 , 葛文翰 , 王俊峰 . 基于对齐原型网络的小样本异常流量分类 [J ] . 四川大学学报(自然科学版) , 2024 , 61 ( 3 ): 9 - 20 .

LIN T C , GE W H , WANG J F . Aligned prototype network for few-shot anomaly traffic classification [J ] . Journal of Sichuan University (Natural Science Edition) , 2024 , 61 ( 3 ): 9 - 20 .

RUWANI M FERNANDO K , TSOKOS C P . Dynamically weighted balanced loss: class imbalanced learning and confidence calibration of deep neural networks [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2022 , 33 ( 7 ): 2940 - 2951 .

窦佳恩 , 张瑛瑛 , 陈玮 . 基于集成学习的物联网攻击检测方法 [J ] . 兵工自动化 , 2024 , 43 ( 8 ): 23 - 26, 59 .

DOU J E , ZHANG Y Y , CHEN W , et al . IoT attack detection method based on ensemble learning [J ] . Ordnance Industry Automation , 2024 , 43 ( 8 ): 23 - 26, 59 .

金志刚 , 丁禹 , 武晓栋 . 融合梯度差分的双边校正联邦入侵检测算法 [J ] . 信息网络安全 , 2024 , 24 ( 2 ): 293 - 302 .

JIN Z G , DING Y , WU X D . Federated intrusion detection algorithm with bilateral correction merging gradient difference [J ] . Netinfo Security , 2024 , 24 ( 2 ): 293 - 302 .

王俊恒 , 朱铭铭 . 基于多原型指导的小样本家族域名入侵检测算法 [J ] . 中国电子科学研究院学报 , 2023 , 18 ( 11 ): 1049 - 1057 .

WANG J H , ZHU M M . Multi-prototype guided few-shot family domain intrusion detection algorithm [J ] . Journal of China Academy of Electronics and Information Technology , 2023 , 18 ( 11 ): 1049 - 1057 .

刘欢 , 肖蔚 , 赵长明 . 基于融合机器学习算法的网络入侵检测与定位技术 [J ] . 现代电子技术 , 2023 , 46 ( 12 ): 182 - 186 .

LIU H , XIAO W , ZHAO C M . Network intrusion detection and location technology based on fused machine learning algorithm [J ] . Modern Electronics Technique , 2023 , 46 ( 12 ): 182 - 186 .

王赞 , 闫明 , 刘爽 , 等 . 深度神经网络测试研究综述 [J ] . 软件学报 , 2020 , 31 ( 5 ): 1255 - 1275 .

WANG Z , YAN M , LIU S , et al . Survey on testing of deep neural networks [J ] . Journal of Software , 2020 , 31 ( 5 ): 1255 - 1275 .

李伟 , 黄鹤鸣 . 基于双交叉熵的自适应残差卷积图像分类算法 [J ] . 计算机工程与设计 , 2023 , 44 ( 12 ): 3670 - 3676 .

LI W , HUANG H M . Adaptive residual convolution image classification algorithm with dual cross-entropy [J ] . Computer Engineering and Design , 2023 , 44 ( 12 ): 3670 - 3676 .

WU Z Y , GUO Y , LIN W F , et al . A weighted deep representation learning model for imbalanced fault diagnosis in cyber-physical systems [J ] . Sensors , 2018 , 18 ( 4 ): 1096 .

AURELIO Y S , DE ALMEIDA G M , DE CASTRO C L , et al . Learning from imbalanced data sets with weighted cross-entropy function [J ] . Neural Processing Letters , 2019 , 50 ( 2 ): 1937 - 1949 .

陈悦 , 杨柳 , 李帅 , 等 . 基于Softmax函数增强卷积神经网络—双向长短期记忆网络框架的交通拥堵预测算法 [J ] . 科学技术与工程 , 2022 , 22 ( 29 ): 12917 - 12926 .

CHEN Y , YANG L , LI S , et al . Traffic congestion prediction algorithm based on CS-BiLSTM framework [J ] . Science Technology and Engineering , 2022 , 22 ( 29 ): 12917 - 12926 .

郭越 . 基于改进CNN的工业控制网络入侵检测研究 [J ] . 机械设计与制造工程 , 2023 , 52 ( 6 ): 103 - 108 .

GUO Y . Research on intrusion detection of industrial control network based on improved CNN [J ] . Machine Design and Manufacturing Engineering , 2023 , 52 ( 6 ): 103 - 108 .

胡佳玲 , 施一萍 , 谢思雅 , 等 . 基于轻量级卷积神经网络人脸识别算法的研究与应用 [J ] . 传感器与微系统 , 2022 , 41 ( 1 ): 153 - 156 .

HU J L , SHI Y P , XIE S Y , et al . Research and application of face recognition algorithm based on lightweight CNN [J ] . Transducer and Microsystem Technologies , 2022 , 41 ( 1 ): 153 - 156 .

RODDA S , EROTHI U S R . Class imbalance problem in the network intrusion detection systems [C ] // Proceedings of the 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT) . Piscataway : IEEE Press , 2016 : 2685 - 2688 .

徐东方 , 徐洪珍 , 邓德军 . 基于CNN-BLSTM-XGB的入侵检测 [J ] . 计算机工程与设计 , 2024 , 45 ( 3 ): 676 - 683 .

XU D F , XU H Z , DENG D J . Intrusion detection based on CNN-BLSTM-XGB [J ] . Computer Engineering and Design , 2024 , 45 ( 3 ): 676 - 683 .

KING G , ZENG L C . Logistic Regression in rare events data [J ] . Political Analysis , 2001 , 9 ( 2 ): 137 - 163 .

Views

106

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An intrusion detection model based on convolution neural network for Internet of vehicles

Optimal approach of suppressing WSN malware propagation based on cloud computing and dynamic Bayesian game

Research of Fragment Mechanism Security in IPv6 Network Protocol

Related Author

ZHANG Rui

Shigen SHEN

Sheng FENG

Haiping ZHOU

Longjun HUANG

Keli HU

Qiying CAO

Xianglin Wang

Related Institution

Department of Information Engineering, Zhumadian Vocatiomal and Technical College

Department of Computer Science and Engineering, Shaoxing University

College of Computer Science and Technology,Donghua University

⁰