MEMCAIN: a memory-enhanced hybrid CNN-attention model for network anomaly detection

Abstract With increasing cybersecurity threats, effective intrusion detection has become critical for safeguarding networks. Although deep learning methods have advanced, two major issues persist: (1) class imbalance biases models toward normal traffic, increasing false negatives; (2) single-task fr...

Full description

Bibliographic Details

Published in:	Scientific Reports
Main Authors:	Lan Liu, Tingfeng Cai, Chiyu Zhou, Fengwei Guo, Kundi Yao, Jianhao Zhou
Format:	Article
Language:	English
Published:	Nature Portfolio 2025-10-01
Subjects:	Network anomaly detection Multi-task learning Class imbalance Memory network
Online Access:	https://doi.org/10.1038/s41598-025-18951-6