Research Article
ConFlow: Contrast Network Flow Improving Class-Imbalanced Learning in Network Intrusion Detection
@INPROCEEDINGS{10.1007/978-3-031-73699-5_9, author={Lan Liu and Pengcheng Wang and Jianliang Ruan and Jun Lin and Junhan Hu}, title={ConFlow: Contrast Network Flow Improving Class-Imbalanced Learning in Network Intrusion Detection}, proceedings={Security and Privacy in New Computing Environments. 6th International Conference, SPNCE 2023, Guangzhou, China, November 25--26, 2023, Proceedings}, proceedings_a={SPNCE}, year={2025}, month={1}, keywords={Cyber security Network intrusion detection system Deep learning Class-imbalanced Contrastive learning}, doi={10.1007/978-3-031-73699-5_9} }- Lan Liu
Pengcheng Wang
Jianliang Ruan
Jun Lin
Junhan Hu
Year: 2025
ConFlow: Contrast Network Flow Improving Class-Imbalanced Learning in Network Intrusion Detection
SPNCE
Springer
DOI: 10.1007/978-3-031-73699-5_9
Abstract
With the increasing complexity and volume of network traffic, accurate detection of malicious network attacks by machine learning-based network intrusion detection systems (NIDSs) remains a challenging task due to imbalanced network traffic. Conventional machine learning algorithms prioritize high overall accuracy without considering class imbalances. To address this issue, we propose ConFlow, a contrastive learning method for network intrusion detection. ConFlow leverages the Dropout layer to obtain two different vector representations of the same traffic, applying supervised contrast loss and cross-entropy loss during training. Experimental results on the ISCX-IDS2012 and CSE-CIC-IDS2017 datasets show that ConFlow outperforms other methods, especially in few-shot learning scenarios, and exhibits high generalization and robustness in real network environments. Our proposed method has significant practical implications for building an intrusion detection system with high accuracy and low false positive rates.
