DDoS Attack Detection in SDN-Assisted Federated Learning Environment Based on Contrastive Learning

Software-defined networking (SDN)-assisted federated learning (FL) is an emerging network computing environment. It can not only shorten the training time of federated learning while maintaining high learning performance, but also enhance the security of the FL network. However, compared with tradit...

Full description

Saved in:
Bibliographic Details
Main Authors: Minghong Fan, Jinghua Lan, Yiyi Zhou, Mengshuang Pan, Junrong Li, Daqiang Zhang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11048486/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849432783083012096
author Minghong Fan
Jinghua Lan
Yiyi Zhou
Mengshuang Pan
Junrong Li
Daqiang Zhang
author_facet Minghong Fan
Jinghua Lan
Yiyi Zhou
Mengshuang Pan
Junrong Li
Daqiang Zhang
author_sort Minghong Fan
collection DOAJ
description Software-defined networking (SDN)-assisted federated learning (FL) is an emerging network computing environment. It can not only shorten the training time of federated learning while maintaining high learning performance, but also enhance the security of the FL network. However, compared with traditional FL networks, SDN-assisted FL technology introduces new security threats. Distributed denial of service(DDoS) attacks are an important security threat for the SDN service in FL. In the SDN-assisted FL environment, the FL network requires the interaction of model parameters among multiple participants. During this process, DDoS attacks may target the SDN control plane, disrupt its normal operation, and thus affect the transmission of model parameters in FL. Hence, this paper proposes a novel approach to detecting and identifying DDoS attacks based on contrastive learning (CL), an adversarial learning framework based on two-layer deep neural networks. The framework features a two-layer classification structure. In the first layer, we integrate Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) to identify DDoS attacks. In the second layer, we enhance the classifier structure by combining Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (BiGRU). This layer can be optimized based on the contrastive classification loss from the LSTM-SVM classifier in the first layer. We conducted experiments on a specific SDN dataset generated by the Mininet emulator. The results show that for the LSTM-SVM model, the detection accuracy reaches 99.75%, and the recall rate is 99.80%. For the CNN-BiGRU model, the detection accuracy rate is 99.36%, and the recall rate is 99.55%. Overall, the proposed CL model can effectively identify DDoS attack traffic in SDN-assisted FL environments, demonstrating high detection performance. However, the model may face challenges such as high computational resource requirements and insufficient adaptability to complex network environments when deployed in practice. Further optimization is needed to facilitate its broader application.
format Article
id doaj-art-3faceafdd662483387286bb728cfc0d7
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-3faceafdd662483387286bb728cfc0d72025-08-20T03:27:17ZengIEEEIEEE Access2169-35362025-01-011310879810881410.1109/ACCESS.2025.358244511048486DDoS Attack Detection in SDN-Assisted Federated Learning Environment Based on Contrastive LearningMinghong Fan0https://orcid.org/0009-0002-8080-2304Jinghua Lan1https://orcid.org/0009-0004-6589-687XYiyi Zhou2Mengshuang Pan3Junrong Li4Daqiang Zhang5https://orcid.org/0000-0002-3812-1225School of Computer Engineering, Jimei University, Xiamen, ChinaDepartment of Computer Science and Engineering, Shaoxing University, Shaoxing, ChinaCollege of Letters and Science, University of California at Berkeley, Berkeley, CA, USADepartment of Computer Science and Engineering, Shaoxing University, Shaoxing, ChinaSchool of Data Science, Lingnan University, Tuen Mun, Hong KongSchool of Software Engineering, Tongji University, Shanghai, ChinaSoftware-defined networking (SDN)-assisted federated learning (FL) is an emerging network computing environment. It can not only shorten the training time of federated learning while maintaining high learning performance, but also enhance the security of the FL network. However, compared with traditional FL networks, SDN-assisted FL technology introduces new security threats. Distributed denial of service(DDoS) attacks are an important security threat for the SDN service in FL. In the SDN-assisted FL environment, the FL network requires the interaction of model parameters among multiple participants. During this process, DDoS attacks may target the SDN control plane, disrupt its normal operation, and thus affect the transmission of model parameters in FL. Hence, this paper proposes a novel approach to detecting and identifying DDoS attacks based on contrastive learning (CL), an adversarial learning framework based on two-layer deep neural networks. The framework features a two-layer classification structure. In the first layer, we integrate Long Short-Term Memory (LSTM) and Support Vector Machine (SVM) to identify DDoS attacks. In the second layer, we enhance the classifier structure by combining Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (BiGRU). This layer can be optimized based on the contrastive classification loss from the LSTM-SVM classifier in the first layer. We conducted experiments on a specific SDN dataset generated by the Mininet emulator. The results show that for the LSTM-SVM model, the detection accuracy reaches 99.75%, and the recall rate is 99.80%. For the CNN-BiGRU model, the detection accuracy rate is 99.36%, and the recall rate is 99.55%. Overall, the proposed CL model can effectively identify DDoS attack traffic in SDN-assisted FL environments, demonstrating high detection performance. However, the model may face challenges such as high computational resource requirements and insufficient adaptability to complex network environments when deployed in practice. Further optimization is needed to facilitate its broader application.https://ieeexplore.ieee.org/document/11048486/Software-defined networkfederated learningdistributed denial of servicesupport vector machinerecurrent neural networklong and short-term memory neural network
spellingShingle Minghong Fan
Jinghua Lan
Yiyi Zhou
Mengshuang Pan
Junrong Li
Daqiang Zhang
DDoS Attack Detection in SDN-Assisted Federated Learning Environment Based on Contrastive Learning
IEEE Access
Software-defined network
federated learning
distributed denial of service
support vector machine
recurrent neural network
long and short-term memory neural network
title DDoS Attack Detection in SDN-Assisted Federated Learning Environment Based on Contrastive Learning
title_full DDoS Attack Detection in SDN-Assisted Federated Learning Environment Based on Contrastive Learning
title_fullStr DDoS Attack Detection in SDN-Assisted Federated Learning Environment Based on Contrastive Learning
title_full_unstemmed DDoS Attack Detection in SDN-Assisted Federated Learning Environment Based on Contrastive Learning
title_short DDoS Attack Detection in SDN-Assisted Federated Learning Environment Based on Contrastive Learning
title_sort ddos attack detection in sdn assisted federated learning environment based on contrastive learning
topic Software-defined network
federated learning
distributed denial of service
support vector machine
recurrent neural network
long and short-term memory neural network
url https://ieeexplore.ieee.org/document/11048486/
work_keys_str_mv AT minghongfan ddosattackdetectioninsdnassistedfederatedlearningenvironmentbasedoncontrastivelearning
AT jinghualan ddosattackdetectioninsdnassistedfederatedlearningenvironmentbasedoncontrastivelearning
AT yiyizhou ddosattackdetectioninsdnassistedfederatedlearningenvironmentbasedoncontrastivelearning
AT mengshuangpan ddosattackdetectioninsdnassistedfederatedlearningenvironmentbasedoncontrastivelearning
AT junrongli ddosattackdetectioninsdnassistedfederatedlearningenvironmentbasedoncontrastivelearning
AT daqiangzhang ddosattackdetectioninsdnassistedfederatedlearningenvironmentbasedoncontrastivelearning