I know I don’t know: an evidential deep learning framework for traffic classification

doi:10.1007/s11704-024-3922-6

Front. Comput. Sci.

2024, Vol. 18

Issue (5) : 185346 https://doi.org/10.1007/s11704-024-3922-6

Artificial Intelligence

I know I don’t know: an evidential deep learning framework for traffic classification

Shangsen LI, Lailong LUO(

), Yun ZHOU, Deke GUO, Xiang XU

National Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410000, China

Download: PDF(2374 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Corresponding Author(s): Lailong LUO

Just Accepted Date: 02 April 2024 Issue Date: 30 April 2024

Cite this article:

Shangsen LI,Lailong LUO,Yun ZHOU, et al. I know I don’t know: an evidential deep learning framework for traffic classification[J]. Front. Comput. Sci., 2024, 18(5): 185346.

URL:

https://academic.hep.com.cn/fcs/EN/10.1007/s11704-024-3922-6
https://academic.hep.com.cn/fcs/EN/Y2024/V18/I5/185346

Fig.1 Our proposed traffic classification framework

Fig.2 Performace of BSA_CE and BSL_CE model

Fig.3 Uncertainty estimation result of EdaTC

Fig.4 The FPR and FNR change according to

θ

	AUC_var	$θ^$	FPR/FNR	AUC_ent	$θ^$	FPR/FNR	AUC_mul	$θ^$	FPR/FNR
MC_BFA	0.9169	0.179589	0.132308	0.9585	0.206277	0.100750	0.9687	0.066278	0.084974
MC_BFL	0.7324	0.168519	0.311261	0.851	0.569718	0.240739	0.9654	0.051725	0.091341
MC_BSA	0.9451	0.182269	0.089815	0.9905	0.381495	0.049791	0.9931	0.115430	0.040437
MC_BSL	0.7273	0.166945	0.283742	0.8423	0.766909	0.266439	0.9732	0.061077	0.093192
MC_MFA	0.7645	0.109668	0.283940	0.8645	0.095713	0.206909	0.9004	0.030432	0.177660
MC_MFL	0.7081	0.123277	0.331513	0.8262	0.414160	0.228796	0.8645	0.067065	0.212942
MC_MSA	0.7558	0.082487	0.294361	0.8287	0.064592	0.231472	0.8719	0.022839	0.191205
MC_MSL	0.7094	0.105639	0.314834	0.8356	0.350706	0.241975	0.8997	0.087567	0.177279

Tab.1 Unknown traffic identify result of MC_dropout

1	I, Guarino G, Aceto D, Ciuonzo A, Montieri V, Persico A Pescapè . Contextual counters and multimodal deep learning for activity-level traffic classification of mobile communication apps during COVID-19 pandemic. Computer Networks, 2022, 219: 109452
2	R, Chen L, Luo Y, Chen J, Xia D Guo . A hybrid framework for class-imbalanced classification. In: Proceedings of the 16th International Conference on Wireless Algorithms, Systems, and Applications. 2021, 301−313
3	J, Zhang X, Chen Y, Xiang W, Zhou J Wu . Robust network traffic classification. IEEE/ACM Transactions on Networking, 2015, 23( 4): 1257–1270
4	S, Le Y, Lai Y, Wang H He . An adaptive classification and updating method for unknown network traffic in open environments. Computer Networks, 2024, 238: 110114
5	J, Zhang F, Li F, Ye H Wu . Autonomous unknown-application filtering and labeling for dl-based traffic classifier update. In: Proceedings of IEEE Conference on Computer Communications. 2020, 397−405
6	M, Shen K, Ye X, Liu L, Zhu J, Kang S, Yu Q, Li K Xu . Machine learning-powered encrypted network traffic analysis: A comprehensive survey. IEEE Communications Surveys & Tutorials, 2023, 25( 1): 791–824
7	W, Wang M, Zhu X, Zeng X, Ye Y Sheng . Malware traffic classification using convolutional neural network for representation learning. In: Proceedings of 2017 International Conference on Information Networking. 2017, 712−717
8	J, Luxemburk T Čejka . Fine-grained TLS services classification with reject option. Computer Networks, 2023, 220: 109467
9	M, Sensoy L, Kaplan M Kandemir . Evidential deep learning to quantify classification uncertainty. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. 2018, 3183−3193
10	A Jøsang . Subjective Logic: A Formalism for Reasoning Under Uncertainty. Cham: Springer, 2016

[1]

FCS-23922-OF-SL_suppl_1

Download

Viewed

Full text

Abstract

Cited

Shared

Discussed