Multiview Correlation-Aware Network Traffic Detection on Flow Hypergraph

Jiajun Zhou

doi:10.1109/JIOT.2025.3627807

2025-12-15

PRE

DOI：10.1109/JIOT.2025.3627807

原文链接

原文求助

摘要

En 中文

As the Internet rapidly expands, the increasing complexity and diversity of network activities pose significant challenges to effective network governance and security regulation. Network traffic, which serves as a crucial data carrier of network activities, has become indispensable in this process. Network traffic detection aims to monitor, analyze, and evaluate the data flows transmitted across the network to ensure network security and optimize performance. However, existing network traffic detection methods generally suffer from several limitations: 1) a narrow focus on characterizing traffic features from a single perspective; 2) insufficient exploration of discriminative features for different traffic; and 3) poor generalization to different traffic scenarios. To address these issues, we propose a multiview correlation-aware framework named FlowID for network traffic detection. FlowID captures multiview traffic features via temporal and interaction awareness, while a hypergraph encoder further explores higher order relationships between flows. To overcome the challenges of data imbalance and label scarcity, we design a dual-contrastive proxy task, enhancing the framework's ability to differentiate between various traffic flows through flow-to-flow and group-to-group contrast. Extensive experiments on five real-world datasets demonstrate that FlowID significantly outperforms existing methods in accuracy, robustness, and generalization across diverse network scenarios, particularly in detecting malicious traffic.

Keyword:

Contrastive learning

cybersecurity

data augmentation

hypergraph

network traffic detection

Contrastive learning

cybersecurity

data augmentation

hypergraph

network traffic detection