Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic Prediction

Current 5G communication services have limitations, prompting the development of the Beyond 5G (B5G) network. B5G aims to extend the scope of communication to encompass land, sea, air, and space while enhancing communication intelligence and evolving into an omnipresent converged information network...

Full description

Saved in:
Bibliographic Details
Main Authors: Lingyao Wang, Chenyue Pan, Haitao Zhao, Mingyi Ji, Xinren Wang, Junchen Yuan, Miao Liu, Donglai Jiao
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/5/1590
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850031220896825344
author Lingyao Wang
Chenyue Pan
Haitao Zhao
Mingyi Ji
Xinren Wang
Junchen Yuan
Miao Liu
Donglai Jiao
author_facet Lingyao Wang
Chenyue Pan
Haitao Zhao
Mingyi Ji
Xinren Wang
Junchen Yuan
Miao Liu
Donglai Jiao
author_sort Lingyao Wang
collection DOAJ
description Current 5G communication services have limitations, prompting the development of the Beyond 5G (B5G) network. B5G aims to extend the scope of communication to encompass land, sea, air, and space while enhancing communication intelligence and evolving into an omnipresent converged information network. This expansion demands higher standards for communication rates and intelligent processing across multiple devices. Furthermore, traffic prediction is crucial for the intelligent and efficient planning and management of communication networks, optimizing resource allocation, and enhancing network performance and communication speeds and is an important part of B5G’s performance. Federated learning addresses privacy and transmission cost issues in model training, making it widely applicable in traffic prediction. However, traditional federated learning models are susceptible to adversarial attacks that can compromise model outcomes. To safeguard traffic prediction from such attacks and ensure the reliability of the prediction system, this paper introduces the Adaptive Threshold Modified Federated Forest (ATMFF). ATMFF employs adaptive threshold modification, utilizing a confusion matrix rate-based screening-weighted aggregation of weak classifiers to adjust the decision threshold. This approach enhances the accuracy of recognizing adversarial samples, thereby ensuring the reliability of the traffic prediction model. Our experiments, based on real 5G traffic data, demonstrate that ATMFF’s adversarial sample recognition accuracy surpasses that of traditional multiboost models and models without adaptive threshold modified. This improvement bolsters the security and reliability of intelligent traffic classification services.
format Article
id doaj-art-b717e7eea3354a3e8a303e731f9f6232
institution DOAJ
issn 1424-8220
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-b717e7eea3354a3e8a303e731f9f62322025-08-20T02:59:01ZengMDPI AGSensors1424-82202025-03-01255159010.3390/s25051590Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic PredictionLingyao Wang0Chenyue Pan1Haitao Zhao2Mingyi Ji3Xinren Wang4Junchen Yuan5Miao Liu6Donglai Jiao7College of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaCollege of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaCollege of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaCollege of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaPortland Institute, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaCollege of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaCollege of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaCollege of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaCurrent 5G communication services have limitations, prompting the development of the Beyond 5G (B5G) network. B5G aims to extend the scope of communication to encompass land, sea, air, and space while enhancing communication intelligence and evolving into an omnipresent converged information network. This expansion demands higher standards for communication rates and intelligent processing across multiple devices. Furthermore, traffic prediction is crucial for the intelligent and efficient planning and management of communication networks, optimizing resource allocation, and enhancing network performance and communication speeds and is an important part of B5G’s performance. Federated learning addresses privacy and transmission cost issues in model training, making it widely applicable in traffic prediction. However, traditional federated learning models are susceptible to adversarial attacks that can compromise model outcomes. To safeguard traffic prediction from such attacks and ensure the reliability of the prediction system, this paper introduces the Adaptive Threshold Modified Federated Forest (ATMFF). ATMFF employs adaptive threshold modification, utilizing a confusion matrix rate-based screening-weighted aggregation of weak classifiers to adjust the decision threshold. This approach enhances the accuracy of recognizing adversarial samples, thereby ensuring the reliability of the traffic prediction model. Our experiments, based on real 5G traffic data, demonstrate that ATMFF’s adversarial sample recognition accuracy surpasses that of traditional multiboost models and models without adaptive threshold modified. This improvement bolsters the security and reliability of intelligent traffic classification services.https://www.mdpi.com/1424-8220/25/5/1590adversarial attackadversarial trainingfederated forestrobustnesstraffic prediction
spellingShingle Lingyao Wang
Chenyue Pan
Haitao Zhao
Mingyi Ji
Xinren Wang
Junchen Yuan
Miao Liu
Donglai Jiao
Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic Prediction
Sensors
adversarial attack
adversarial training
federated forest
robustness
traffic prediction
title Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic Prediction
title_full Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic Prediction
title_fullStr Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic Prediction
title_full_unstemmed Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic Prediction
title_short Highly Accurate Adaptive Federated Forests Based on Resistance to Adversarial Attacks in Wireless Traffic Prediction
title_sort highly accurate adaptive federated forests based on resistance to adversarial attacks in wireless traffic prediction
topic adversarial attack
adversarial training
federated forest
robustness
traffic prediction
url https://www.mdpi.com/1424-8220/25/5/1590
work_keys_str_mv AT lingyaowang highlyaccurateadaptivefederatedforestsbasedonresistancetoadversarialattacksinwirelesstrafficprediction
AT chenyuepan highlyaccurateadaptivefederatedforestsbasedonresistancetoadversarialattacksinwirelesstrafficprediction
AT haitaozhao highlyaccurateadaptivefederatedforestsbasedonresistancetoadversarialattacksinwirelesstrafficprediction
AT mingyiji highlyaccurateadaptivefederatedforestsbasedonresistancetoadversarialattacksinwirelesstrafficprediction
AT xinrenwang highlyaccurateadaptivefederatedforestsbasedonresistancetoadversarialattacksinwirelesstrafficprediction
AT junchenyuan highlyaccurateadaptivefederatedforestsbasedonresistancetoadversarialattacksinwirelesstrafficprediction
AT miaoliu highlyaccurateadaptivefederatedforestsbasedonresistancetoadversarialattacksinwirelesstrafficprediction
AT donglaijiao highlyaccurateadaptivefederatedforestsbasedonresistancetoadversarialattacksinwirelesstrafficprediction