MamNet: A Novel Hybrid Model for Time-Series Forecasting and Frequency Pattern Analysis in Network Traffic

2025-06-30

AI Summary

Network traffic anomalies often signal security threats or system failures, necessitating detection methods that jointly model temporal dynamics and spectral characteristics. To address this, we propose a multi-scale time-frequency modeling framework that integrates the Mamba architecture with Fourier transform: Mamba efficiently captures long-range temporal dependencies, while Fourier analysis explicitly models periodic patterns in the frequency domain; a lightweight feature fusion mechanism further enables complementary time-frequency representation learning. Evaluated on the UNSW-NB15 and CAIDA datasets, our method outperforms state-of-the-art baselines across accuracy, recall, and F1-score. It achieves 2–4% improvement in detecting complex anomalous patterns and significantly enhances robustness and interpretability for anomaly identification in highly dynamic network environments.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Security and Privacy: Large-scale security measurements

Abstract

The abnormal fluctuations in network traffic may indicate potential security threats or system failures. Therefore, efficient network traffic prediction and anomaly detection methods are crucial for network security and traffic management. This paper proposes a novel network traffic prediction and anomaly detection model, MamNet, which integrates time-domain modeling and frequency-domain feature extraction. The model first captures the long-term dependencies of network traffic through the Mamba module (time-domain modeling), and then identifies periodic fluctuations in the traffic using Fourier Transform (frequency-domain feature extraction). In the feature fusion layer, multi-scale information is integrated to enhance the model's ability to detect network traffic anomalies. Experiments conducted on the UNSW-NB15 and CAIDA datasets demonstrate that MamNet outperforms several recent mainstream models in terms of accuracy, recall, and F1-Score. Specifically, it achieves an improvement of approximately 2% to 4% in detection performance for complex traffic patterns and long-term trend detection. The results indicate that MamNet effectively captures anomalies in network traffic across different time scales and is suitable for anomaly detection tasks in network security and traffic management. Future work could further optimize the model structure by incorporating external network event information, thereby improving the model's adaptability and stability in complex network environments.

Problem

• Detects network traffic anomalies via time-frequency hybrid modeling
• Improves accuracy in identifying security threats and system failures
• Enhances long-term trend and periodic pattern detection performance

Innovation

• Hybrid model combining time and frequency domains
• Mamba module for long-term traffic dependencies
• Fourier Transform for periodic fluctuation analysis