A Railway Mobile Terminal Malware Detection Method Based on SE-ResNet
Source abstract
Abstract
This paper proposes a residual network model integrated with an attention mechanism module for the detection and classification of malware on railway mobile terminals. To address the issues of insufficient and imbalanced samples, Wasserstein Generative Adversarial Networks (WGANs) are utilized to synthesize grayscale image data of malware with high similarity to real samples. The performance of the model is evaluated on the publicly available CIC-InvesAndMal2019 dataset and an extended balanced dataset. Experimental results demonstrate that the synergistic integration of residual networks, WGANs, and attention mechanisms significantly enhances the performance of the malware detection model. In the context of railway applications, the proposed approach also achieves favorable classification performance when applied to image datasets derived from malware samples of railway mobile terminals. Multiple ablation studies are conducted to individually validate the contributions of each technical component in improving the classification model’s efficacy. The adoption of the SE-ResNet architecture combined with WGAN-based data augmentation presents a practical and efficient technical solution.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Malware Detection Techniques · Network Security and Intrusion Detection · Fire Detection and Safety Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Cyberspace Science and Technology, Beijing Jiaotong University, Beijing 100044, China
Institute of Electronic Computing Technology, China Academy of Railway Sciences Corporation Limited, Beijing 100081, China
Funding
the Natural Science Foundation of China Academy of Railway Sciences Corporation Limited
References (26)
Show source-provided references
1. (2024). Guidelines for Railway Cybersecurity Inspection (Provisional) (Standard No. TJ/XX 013-2024).
2. Malicious Code Detection Based on Feature Fusion
3. Zhi, Z., Yukai, Y., Yiling, S., Wenjin, M., and Chang, P. (2025). Research on Android Malware Detection Model Based on Multimodal Feature Fusion. Comput. Eng., 1–12. Available online: https://aipub.cn/JzH87N5.
4. A Malicious Code Detection Technology Based on Static API Calls and Ensemble Learning
5. Chijun, L. (2025). Research and Implementation of Malicious Code Detection System Based on Heuristic Algorithm [D]. [Ph.D. Thesis, Nanjing University of Posts and Telecommunications].
6. A Survey of Malware Recognition Research Based on Machine Learning
7. Malicious Code Behavior Detection Method Based on Sandbox Technology
8. A Linux Malware Detection Scheme Based on Virtual Machine Introspection
9. Design and Implementation of a Lightweight Linux Sandbox Based on Multiple Security Mechanisms
10. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
11. Ziheng, R. (2024). Research and Implementation of Malicious Code Detection Technology Based on Deep Learning. [Ph.D. Thesis, Beijing University of Posts and Telecommunications [D]].
12. Malicious Code Detection and Classification Based on GHM Visualization and Deep Learning
13. Data-driven models for train control dynamics in high-speed railways: LAG-LSTM for train trajectory prediction10.1016/j.ins.2022.04.004 ↗
14. A Ransomware Classification Method Based on Hilbert Curve-Residual Network
15. A Cybersecurity Situation Awareness Method Based on Residual Convolutional Neural Network
16. A Cybersecurity Entity Recognition Method Based on Residual Dilated Convolutional Neural Network
17. Malicious code detection method based on attention mechanism and residual network
18. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial networks. Proceedings of the International Conference on Neural Information Processing System, Montreal, QC, Canada.
19. Ledig, C., Theis, L., Huszár, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., and Wang, Z. (2017, January 21–26). Photo-realistic single image super-resolution using a generative adversarial network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.19 ↗
20. Bai, Y., Zhang, Y., Ding, M., and Ghanem, B. (2018, January 8–14). Sod-mtgan: Small object detection via multi-task generative adversarial network. Proceedings of the European Conference n Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01261-8_13 ↗
21. Yu, L., Zhang, W., Wang, J., and Yong, Y. (2017, January 4–9). Seqgan: Sequence generative adversarial nets with policy gradient. Proceedings of the AAAI Conference on Artificial Intelligence, San Fracisco, CA, USA.10.1609/aaai.v31i1.10804 ↗
22. Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6–11). Wasserstein generative adversarial networks. Proceedings of the International Conference on Machine Learning, PMLR, Sydney, NSW, Australia.
23. Arjovsky, M., and Bottou, L. (2017). Towards principled methods for training generative adversarial networks. arXiv.
24. A Family Tracing Method for Malicious Code Variants Based on Generative Adversarial Networks
25. An Imbalanced Data Augmentation Method Based on Generative Adversarial Networks for Intrusion Detection
26. Burks, R., Islam, K.A., Li, J., and Lu, Y. (2019, January 10–12). Data Augmentation with Generative Models for Improved Malware Detection: A Comparative Study. Proceedings of the IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference, IEEE, New York, NY, USA.10.1109/UEMCON47517.2019.8993085 ↗