《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (4): 1201-1206.DOI: 10.11772/j.issn.1001-9081.2021071276

• CCF第36届中国计算机应用大会 (CCF NCCA 2021) • 上一篇    

基于麻雀搜索算法和改进粒子群优化算法的网络入侵检测算法

高兵1, 郑雅1, 秦静2, 邹启杰1, 汪祖民1()   

  1. 1.大连大学 信息工程学院,辽宁 大连 116622
    2.大连大学 软件工程学院,辽宁 大连 116622
  • 收稿日期:2021-07-16 修回日期:2021-09-10 接受日期:2021-09-10 发布日期:2022-04-15 出版日期:2022-04-10
  • 通讯作者: 汪祖民
  • 作者简介:高兵(1976—),男,黑龙江哈尔滨人,高级工程师,博士,CCF会员,主要研究方向:数据挖掘、大数据
    郑雅(1997—),女,山东济南人,硕士研究生,CCF会员,主要研究方向:网络安全
    秦静(1981—),女,甘肃张掖人,副教授,博士,CCF会员,主要研究方向:信号处理、大数据分析
    邹启杰(1978—),女,黑龙江牡丹江人,副教授,博士,CCF会员,主要研究方向:智能规划与决策、计算机视觉、机器学习
  • 基金资助:
    国家自然科学基金资助项目(62002038);辽宁省科学研究项目(LJKZ1180)

Network intrusion detection algorithm based on sparrow search algorithm and improved particle swarm optimization algorithm

Bing GAO1, Ya ZHENG1, Jing QIN2, Qijie ZOU1, Zumin WANG1()   

  1. 1.College of Information Engineering,Dalian University,Dalian Liaoning 116622,China
    2.College of Software Engineering,Dalian University,Dalian Liaoning 116622,China
  • Received:2021-07-16 Revised:2021-09-10 Accepted:2021-09-10 Online:2022-04-15 Published:2022-04-10
  • Contact: Zumin WANG
  • About author:GAO Bing, born in 1976, Ph. D., senior engineer. His research interests include data mining, big data.
    ZHENG Ya, born in 1997, M. S. candidate. Her research interests include network security.
    QIN Jing, born in 1981, Ph. D., associate professor. Her research interests include signal processing, big data analysis.
    ZOU Qijie, born in 1978, Ph. D., associate professor. Her research interests include intelligent planning and decision making, computer vision, machine learning.
  • Supported by:
    National Natural Science Foundation of China(62002038);Scientific Research Project of Liaoning Province(LJKZ1180)

摘要:

针对网络入侵检测模型自适应能力不足的问题,将麻雀搜索算法(SSA)中的大范围快速搜索能力引入到粒子群优化(PSO)算法,提出基于麻雀搜索算法的改进粒子群优化(SSAPSO)算法。该算法通过对轻量级梯度提升机(LightGBM)算法中难以整定的参数进行寻优,使PSO算法在保证寻优精度的同时快速收敛,并得到最优的网络入侵检测模型。仿真实验结果表明,在4种基准函数上,SSAPSO比基本PSO算法收敛速度更快;在KDDCUP99数据集上,SSAPSO优化LightGBM后得到的SSAPSO-LightGBM算法比分类特征和梯度提升(CatBoost)算法的准确率、召回率、精确率和F1指数分别提升了15.12%、3.25%、21.26%和12.25%;SSAPSO-LightGBM算法在上述数据集中正常流量(Normal)、未授权远程访问(R2L)攻击、未授权本地访问(U2R)攻击、监听(PROBE)攻击的检测准确率比LightGBM算法分别提升了0.61%、3.14%、4.24%、1.04%和5.03%。

关键词: 监督学习, 粒子群优化算法, 麻雀搜索算法, 入侵检测, 参数寻优

Abstract:

Aiming at the problem of insufficient adaptive ability of network intrusion detection models, the large-scale fast search ability of Sparrow Search Algorithm (SSA) was introduced into Particle Swarm Optimization (PSO) algorithm, and a network intrusion detection algorithm based on Sparrow Search Algorithm and improved Particle Swarm Optimization Algorithm (SSAPSO) was proposed. In the algorithm, by optimizing the parameters that are difficult to set in Light Gradient Boosting Machine (LightGBM) algorithm, PSO algorithm converged quickly while ensuring the optimization accuracy, and an optimal network intrusion detection model was obtained. Simulation results show that on the four benchmark functions, SSAPSO converged faster than basic PSO algorithm. Compared with Categorical features+gradient Boosting (CatBoost) algorithm, SSAPSO optimized LightGBM (SSAPSO-LightGBM) has the accuracy, recall, precision and F1_score improved by 15.12%, 3.25%, 21.26% and 12.25% respectively on KDDCUP99 dataset. Compared with LightGBM algorithm, SSAPSO-LightGBM has the detection accuracy for Normal, Remote-to-Login (R2L) attack, User-to-Root (U2R) attack and Probeing (PROBE) attack on the above dataset improved by 0.61%, 3.14%, 4.24%, 1.04% and 5.03% respectively.

Key words: supervised learning, Particle Swarm Optimization (PSO) algorithm, Sparrow Search Algorithm (SSA), intrusion detection, parameter optimization

中图分类号: