计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (2): 336-343.doi: 10.11896/jsjkx.240300031

• 信息安全 • 上一篇    下一篇

基于通用扰动的对抗网络流量生成方法

丁瑞阳1, 孙磊1, 戴乐育1, 臧韦菲1, 徐八一1,2   

  1. 1 信息工程大学密码工程学院 郑州 450001
    2 郑州大学网络空间安全学院 郑州 450000
  • 收稿日期:2024-03-05 修回日期:2024-07-16 出版日期:2025-02-15 发布日期:2025-02-17
  • 通讯作者: 孙磊(sl20210221@163.com)
  • 作者简介:(dry23120229306@163.com)

Generation Method for Adversarial Networks Traffic Based on Universal Perturbations

DING Ruiyang1, SUN Lei1, DAI Leyu1, ZANG Weifei1, XU Bayi1,2   

  1. 1 Department of Cryptogram Engineering,Information Engineering University,Zhengzhou 450001,China
    2 School of Cyberspace Security,Zhengzhou University,Zhengzhou 450000,China
  • Received:2024-03-05 Revised:2024-07-16 Online:2025-02-15 Published:2025-02-17
  • About author:DING Ruiyang,born in 2000,postgra-duate.His main research interests include cyberspace security and artificial intelligence security.
    SUN Lei,born in 1973,professor.His main research interests include artificial intelligence and information systems security.

PDF (PC)

115

摘要： 人工智能技术在网络流量分类领域表现出了巨大潜力,对网络空间安全的战略格局产生了深刻影响。但也有研究发现,深度学习模型有着严重的脆弱性,针对该脆弱性衍生的对抗样本可以大幅度降低模型检测的正确率。目前对抗样本在图像分类领域得到了广泛深入的研究,在网络流量分类领域还处于发展阶段。现有的对抗网络流量技术仅对特定样本有效,并且时间开销较大、实用性低。为此,提出了基于通用扰动的对抗网络流量生成方法,其利用空间特征分布的性质寻找通用扰动向量,将该扰动添加到正常流量生成对抗网络流量,令网络流量分类器以高概率检测错误。在Moore和ISCX2016数据集上与现有方法进行了实验测试。结果表明,同等条件下,该方法生成对抗网络流量攻击分类器时对Moore和ISCX2016数据集内样本均有效,成功率高达80%以上;并且可以有效攻击不同的分类器,具有模型迁移性效果;同时实现了对抗网络流量的快速生成,平均生成时间开销低于1 ms,效率远优于现有方法。

关键词: 深度学习, 网络流量分类, 对抗网络流量, 通用扰动

Abstract: Artificial intelligence technology has shown great potential in the field of network traffic classification and has had a profound impact on the strategic landscape of cyberspace security.But some studies have also found that deep learning models have serious vulnerabilities,and adversarial samples derived from this vulnerability can significantly reduce the accuracy of model detection.At present,adversarial samples are widely and deeply studied in the field of image classification,and are still in the development stage in the field of network traffic classification.The existing adversa-rial network traffic technology is only effective for specific samples,and has high time cost and low practicality.Therefore,this paper proposes a method for generating adversarialnetwork traffic based on general perturbations.It uses the properties of spatial feature distribution to find a general perturbation vector,adds this perturbation to normal traffic to generate adversarial network traffic,and causes a high probability of detection errors in the network traffic classifier.Compared with existing methods,this paper conducts experimental tests on Moore dataset and ISCX2016 dataset.The results show that under the same conditions,this method is effective for generating adversarial network traffic attack classifiers for all samples on Moore dataset and ISCX2016 dataset,with a success rate of over 80%.It can effectively attack different classifiers,with model transferability effect.At the same time,the time cost is less than 1 ms,achieving rapid generation of adversarial network traffic with much higher efficiency than existing methods.

Key words: Deep learning, Network traffic classification, Adversarial network traffic, Universal perturbations

中图分类号: 

  • TP393
[1]CHALAPATHY R,CHAWLA S.Deep Learning for Anomaly Detection:A Survey[J].arXiv:1901.03407,2019.
[2]JIN K,ZHANG L,ZHANG Y J,et al.A Network Traffic Intrusion Detection Method for Industrial Control Systems Based on Deep Learning[J].Electronics,2023,12(20):4329.
[3]KWON D,KIM H,KIM J,et al.A survey of deep learning-based network anomaly detection[J].Cluster Computing,2019,22:949-961.
[4]LASHKARI A H,KADIR A F A,GONZALEZ H,et al.Towards a network-based framework for android malware detection and characterization[C]//2017 15th Annual Conference on Privacy,Security and Trust(PST).IEEE,2017.
[5]RING M,LANDES D,HOTHO A.Detection of slow port scans in flow-based network traffic[J].PLoS One,2018,13(9):e0204507.
[6]LIU J X,SONG X C,ZHOU Y J,et al.Deep anomaly detection in packet payload[J].Neuro computing,2022,485:205-218.
[7]REZAEI S,LIU X.Deep learning for encrypted traffic classification:An overview[J].IEEE Communications Sagazine,2019,57(5):76-81.
[8]ABBASI M,SHAHRAKI A,TAHERKORDI A.Deep learning for network traffic monitoring and analysis(NTMA):A survey[J].Computer Communications,2021,170:19-41.
[9]LI J W,PAN Z S.Network traffic classification based on deep learning[J].KSII Transactions on Internet and Information Systems(TIIS),2020,14(11):4246-4267.
[10]LIM H K,KIM J B,HEO J S,et al.Packet-based network traffic classification using deep learning[C]//2019 International Conference on Artificial Intelligence in Information and Communication(ICAIIC).IEEE,2019:46-51.
[11]SADEGHZADEH A M,SHIRAVI S,JALILI R.Adversarialnetwork traffic:Towards evaluating the robustness of deep-learning-based network traffic classification[J].IEEE Transactions on Network and Service Management,2021,18(2):1962-1976.
[12]WANG Y,LU B,ZHU Y F.Generation and Application of Adversarial Network Traffic:A Survey [J].Computer Science,2022,49(S2):651-661.
[13]HU Y J,GUO Y B,MA J,et al.Method to generate cyber deception traffic based on adversarial sample [J].Journal on Communication/Tongxin Xuebao,2020,41(9):59-70.
[14]RIGAKI M.Adversarial deep learning against intrusion detection classifiers[J].EUR Workshop Proceedings,2017,2057:35-48.
[15]IBITOYE O,SHAFIQ O,MATRAWY A.Analyzing adversarial attacks against deep learning for intrusion detection in IoT networks[C]//2019 IEEE Global Communications Conference(GLOBECOM).IEEE,2019:1-6.
[16]HU Y J,TIAN J,MA J.A novel way to generate adversarial network traffic samples against network traffic classification[J].Wireless Communications and Mobile Computing,2021,2021:1-12.
[17]YAN Q,WANG M D,HUANG W Y,et al.Automatically synthesizing DoS attack traces using generative adversarial networks[J].International Journal of Machine Learning and Cybernetics,2019,10(12):3387-3396.
[18]HASHEMI M J,CUSACK G,KELLER E.Towards evaluation of nidss in adversarial setting[C]//Proceedings of the 3rd ACM Conext Workshop on Big Data,Machine Learning and Artificial Intelligence for Data Communication Networks.2019:14-21.
[19]USAMA M,QAYYUM A,QADIR J,et al.Black-box adversa-rial machine learning attack on network traffic classification[C]//2019 15th International Wireless Communications & Mobile Computing Conference(IWCMC).IEEE,2019:84-89.
[20]MOOSAVI-DEZFOOLI S M,FAWZI A,FAWZI O,et al.Universal adversarial perturbations[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1765-1773.
[21]KRUPSKI J,GRANISZEWSKI W,IWANOWSKI M.Datatransformation schemes for cnn-based network traffic analysis:A survey[J].Electronics,2021,10(16):2042.
[22]MOORE A W,ZUEV D.Internet traffic classification usingbayesian analysis techniques[C]//Proceedings of the 2005 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems.Banff,2005:50-60.
[23]DRAPER-GIL G,LASHKARI A H,MAMUN M S I,et al.Characterization of encrypted and vpn traffic using time-related[C]//Proceedings of the 2nd International Conference on Information Systems Security and Privacy(ICISSP).2016:407-414.
[24]YANG Y H,SUN L,DAI L Y,et al.Generate Transferable Adversarial Network Traffic Using Reversible Adversarial Padding[J].Computer Science,2023,50(12):359-367.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发