A stable noise injection method and robust learning framework for malicious traffic detection
The Computer Journal · 20.08.2026 · 69 (8) · 1303-1319
DOI: 10.1093/comjnl/bxag027 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Computer Journal, online erschienen am 17.03.2026. Verfasst von Degang Li und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Gefördert von: National Key R&D Program of China, Natural Science Foundation of Henan.
Abstract (Originalsprache)
Noise injection methods evaluate the generalization and robustness of malicious traffic detection models by corrupting clean dataset labels to produce diverse noisy label datasets. This study systematically analyzes the impact of existing noise injection methods on model performance and reveals that high-noise-rate datasets often distort the labels of simple samples, yielding noise distributions inconsistent with real-world scenarios. To overcome this issue, we propose S-IDN, a malicious traffic noise injection method that generates a more stable noise distribution closely aligned with realistic labeling errors. Experimental results show that the stability of S-IDN surpasses that of existing methods by 57.4% and 81.9% on two benchmark datasets. Furthermore, we introduce Robust Label, a robust learning framework for malicious traffic detection. By evaluating label robustness during training, it selects clean and noisy samples adaptively and employs multiple loss functions to construct precise decision boundaries. Under extreme noise conditions (noise rate = 0.9), Robust Label achieves accuracy above 80% for binary detection and 60% for multiclass detection, outperforming the best existing models by up to 13.01% and 9.34%, respectively. Extensive experimental results demonstrate the superior efficiency and robustness of Robust Label for malicious traffic detection.
Förderung
- National Key R&D Program of China
- Natural Science Foundation of Henan
Zitieren
APA
Li, D., Chen, X., Yuan, Q., & Gu, C. (2026). A stable noise injection method and robust learning framework for malicious traffic detection. The Computer Journal, 69(8), 1303-1319. https://doi.org/10.1093/comjnl/bxag027
Vancouver
Li D, Chen X, Yuan Q, Gu C. A stable noise injection method and robust learning framework for malicious traffic detection. The Computer Journal. 2026;69(8):1303-1319. doi:10.1093/comjnl/bxag027
BibTeX
@article{Li2026,
author = {Li, Degang and Chen, Xi and Yuan, Qingjun and Gu, Chunxiang},
title = {A stable noise injection method and robust learning framework for malicious traffic detection},
journal = {The Computer Journal},
year = {2026},
volume = {69},
number = {8},
pages = {1303--1319},
doi = {10.1093/comjnl/bxag027}
}
EUVIMED