Application of Transformer-Based Architectures for Detecting Evolving Malware Patterns in Large-Scale Network Logs

John Robert Lim

Authors

John Robert Lim Independent Researcher, United Kingdom. Author

Keywords:

Malware Detection, Transformer Networks, Network Logs, Deep Learning, Anomaly Detection, Evolving Patterns, Large-Scale Data

Abstract

The detection of evolving malware patterns in large-scale network logs is a challenging task due to the rapid pace at which malware techniques change and the massive volume of data involved. This paper explores the application of transformer-based architectures, commonly used in natural language processing (NLP), for malware detection in network traffic. Transformer models' ability to handle sequential data and capture long-range dependencies makes them well-suited for analyzing network logs. We propose a deep learning framework that leverages transformers to identify and adapt to new malware patterns in real-time. The effectiveness of the proposed framework is validated using benchmark datasets, showing significant improvements in detection accuracy compared to traditional methods.

References

Zhang, L., Liu, Z., & Chen, X. (2020). Challenges of traditional signature-based methods in detecting evolving malware. Journal of Cybersecurity and Network Defense, 22(4), 145-160.

Kamadi, S. (2023). Identity-Driven Zero Trust Automation in GitOps: Policy-as-Code Enforcement for Secure Code Deployments. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 9(3), 893-902. https://doi.org/10.32628/CSEIT235148

Liu, Q., & Wang, Y. (2019). Using recurrent neural networks for sequence-based anomaly detection in network traffic. International Journal of Machine Learning in Cybersecurity, 11(2), 101-112.

Xie, J., Wang, F., & Li, H. (2021). Time-series anomaly detection using transformer models for network security applications. IEEE Transactions on Neural Networks, 32(5), 1789-1801.

Huang, G., Lee, P., & Sun, D. (2020). Applying transformers to cybersecurity for novel malware detection. Journal of Information Security, 18(3), 202-216.

Sharma, A., Kumar, R., & Gupta, P. (2022). Hybrid models combining transformers with convolutional layers for enhanced malware detection. Journal of Machine Learning in Security, 6(2), 50-65.

Kamadi, S. (2022). Adaptive Federated Data Science & MLOps Architecture: A Comprehensive Framework for Distributed Machine Learning Systems. International Journal of Scientific Research in Computer Science, Engineering and Information Technology (IJSRCSEIT), 8(6), 745-755. https://doi.org/10.32628/CSEIT22555

Pham, L., & Ha, T. (2021). Deep packet inspection and machine learning models for identifying network anomalies. Journal of Network and Information Security, 29(1), 60-75.

Silva, C., Costa, J., & Oliveira, L. (2021). Neural networks for detecting unknown malware patterns without decryption. International Journal of Cloud Security, 19(2), 88-102.

Yu, F., & Zhang, J. (2020). Recent advancements in machine learning-based malware detection systems. Cybersecurity Review, 10(3), 123-134.

Kamadi, S. (2022). Proactive cybersecurity for enterprise APIs: Leveraging AI-driven intrusion detection systems in distributed Java environments. International Journal of Research in Computer Applications and Information Technology, 5(1), 34-52. https://doi.org/10.34218/IJRCAIT_05_01_004

Yang, S., & Li, Y. (2020). RNN-based models for dynamic malware pattern detection in network traffic. Journal of Computing and Information Security, 14(4), 92-105.

Wu, C., & Zhang, H. (2021). Deep learning applications for evolving malware detection in cloud environments. IEEE Cloud Computing Journal, 13(5), 135-145.

Xu, Q., & Zhang, S. (2020). Enhancing anomaly detection in large-scale network traffic using transformers. Journal of Artificial Intelligence and Cybersecurity, 8(1), 56-72.

Chen, T., & Huang, L. (2020). Transformer-based architectures for malware detection in network logs. Journal of Cyber Threat Detection, 12(6), 34-48.

Liu, S., & Liu, X. (2021). A comparative study of deep learning models for malware detection in real-time network traffic. Journal of Computer Science and Security, 19(4), 120-134.

Chen, W., & Zhang, K. (2020). Detection of evolving malware patterns with deep learning techniques. International Journal of Network Security and Cryptography, 14(3), 105-118.