《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (10): 3231-3240.DOI: 10.11772/j.issn.1001-9081.2024101457

• 网络空间安全 • 上一篇    

基于混合特征选择的低延时DDoS攻击检测

谢丽霞1, 王嘉敏1, 杨宏宇1,2(), 胡泽2, 成翔3,4   

  1. 1.中国民航大学 计算机科学与技术学院,天津 300300
    2.中国民航大学 安全科学与工程学院,天津 300300
    3.扬州大学 信息工程学院,江苏 扬州 225127
    4.中国民航大学 民航信息安全评估中心,天津 300300
  • 收稿日期:2024-10-16 修回日期:2025-01-18 接受日期:2025-01-22 发布日期:2025-02-07 出版日期:2025-10-10
  • 通讯作者: 杨宏宇
  • 作者简介:谢丽霞(1974—),女,重庆人,教授,博士,CCF高级会员,主要研究方向:网络信息安全
    王嘉敏(1998—),女,河南安阳人,硕士研究生,主要研究方向:网络信息安全、DDoS攻击检测
    杨宏宇(1969—),男,吉林长春人,教授,博士生导师,博士,CCF高级会员,主要研究方向:网络与系统安全、软件安全检测、网络安全态势感知 Email:yhyxlx@hotmail.com
    胡泽(1989—),男,山西临汾人,讲师,博士,主要研究方向:人工智能、自然语言处理、网络信息安全
    成翔(1989—),男,新疆乌鲁木齐人,实验师,博士,主要研究方向:网络与系统安全、网络安全态势感知、APT攻击检测。
  • 基金资助:
    国家自然科学基金民航联合研究基金重点项目(2433205);江苏省基础研究计划自然科学基金青年基金资助项目(BK20230558)

Low-latency DDoS attack detection based on hybrid feature selection

Lixia XIE1, Jiamin WANG1, Hongyu YANG1,2(), Ze HU2, Xiang CHENG3,4   

  1. 1.College of Computer Science and Technology,Civil Aviation University of China,Tianjin 300300,China
    2.College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China
    3.College of Information Engineering,Yangzhou University,Yangzhou Jiangsu 225127,China
    4.Information Security Evaluation Center of Civil Aviation,Civil Aviation University of China,Tianjin 300300,China
  • Received:2024-10-16 Revised:2025-01-18 Accepted:2025-01-22 Online:2025-02-07 Published:2025-10-10
  • Contact: Hongyu YANG
  • About author:XIE Lixia, born in 1974, Ph. D., professor. Her research interestsinclude network information security.
    WANG Jiamin,born in 1998, M. S. candidate. Her researchinterests include network information security, DDoS attack detection.
    YANG Hongyu, born in 1969, Ph. D., professor. His researchinterests include network and system security, software security detection, network security situation awareness.
    HU Ze,born in 1989, Ph. D., lecturer. His research interestsinclude artificial intelligence, natural language processing, network information security
    CHENG Xiang, born in 1989, Ph. D., experimentalist. Hisresearch interests include network and system security, network security situation awareness, APT attack detection.

摘要:

许多分布式拒绝服务(DDoS)攻击检测方法侧重提升模型性能,但忽略流量样本分布和特征维度对检测性能的影响,导致模型学习多余信息。针对网络流量类不平衡和特征冗余问题,提出一种基于多评价标准的混合特征选择方法(HFS-MEC)。首先,综合考虑皮尔逊相关系数(PCC)和互信息(MI),选出相关性特征;其次,设计基于方差膨胀因子(VIF)的序列后向选择(SBS)算法,减少特征冗余,进一步降低特征维度;同时,为了平衡检测性能和计算时间,设计基于简单循环单元(SRU)的低延时DDoS攻击检测(L-DDoS-SRU)模型。在CICIDS2017和CICDDoS2019数据集上的实验结果表明,HFS-MEC将特征维度从78和88分别减少至31和41。在CICDDoS2019数据集上,L-DDoS-SRU检测时间仅40.34 s;召回率达99.38%,与长短期记忆(LSTM)相比提高了8.47%,与门控循环单元(GRU)相比提高了9.76%。以上验证了所提方法能有效提高检测性能并减少检测时间。

关键词: 类不平衡, 特征冗余, 混合特征选择, 低延时, 分布式拒绝服务攻击检测, 简单循环单元

Abstract:

Many Distributed Denial of Service (DDoS) attack detection methods focus on improving model performance, but ignore the influence of traffic sample distribution and feature dimension on detection performance, resulting in the model learning redundant information. To address the problems of network traffic class imbalance and feature redundancy, a Hybrid Feature Selection method based on Multiple Evaluation Criteria (HFS-MEC) was proposed. Firstly, the Pearson Correlation Coefficient (PCC) and Mutual Information (MI) were considered comprehensively to select the correlation features. Then, the Sequential Backward Selection (SBS) algorithm based on Variance Inflation Factor (VIF) was designed to reduce the feature redundancy and further reduce the feature dimension. At the same time, to balance the detection performance and computation time, a Low-latency DDoS attack detection model based on Simple Recurrent Unit (SRU) (L-DDoS-SRU) was designed. Experiments were carried out on the CICIDS2017 and CICDDoS2019 datasets. The results show that HFS-MEC reduces the feature dimensions from 78 and 88 to 31 and 41, respectively; on the CICDDoS2019 dataset, L-DDoS-SRU reduces the detection time to only 40.34 seconds with a recall of 99.38%, which is improved by 8.47% compared to that of Long Short-Term Memory (LSTM), and is increased by 9.76% compared to that of Gated Recurrent Unit (GRU). The above verifies that the proposed method improves the detection performance and reduces the detection time effectively.

Key words: class imbalance, feature redundancy, hybrid feature selection, low-latency, Distributed Denial of Service (DDoS) attack detection, Simple Recurrent Unit (SRU)

中图分类号: