Leveraging Transfer Learning for Enhanced Internet Security: Methods and Applications

Chang Chen

doi:10.62051/aa842m92

Authors

Chang Chen

DOI:

https://doi.org/10.62051/aa842m92

Keywords:

Transfer Learning; Internet Security; Data Imbalance; Network Attacks.

Abstract

Internet technology is developing rapidly today. It not only brings new experiences to people but also brings huge security risks. The attack methods of cyber criminals are becoming more and more complex and unpredictable. The rise of artificial intelligence offers promising solutions for detecting and mitigating network attacks, but challenges such as insufficient and imbalanced datasets continue to hinder the effectiveness of these models. Transfer learning has emerged as a valuable technique to address these challenges by transferring knowledge and parameters from a source domain model to a target domain. This approach can reduce training costs, save time, enhance data utilization, and address data imbalance issues. This article provides a detailed examination of transfer learning, including its definition, methodologies, and specific applications within the Internet domain. It explores three key scenarios: network anomaly detection, malicious domain name detection, and rumor detection. By offering a comprehensive overview of transfer learning and its practical implementations, this paper hopes to help readers acquire a clear and comprehensive concept of transfer learning and its relevance to Internet security, serving as a valuable resource for those interested in this field.

Downloads

Download data is not yet available.

References

[1] Shone N. Ngoc T.N. Phai V.D. et al. A deep learning approach to network intrusion detection. IEEE transactions on emerging topics in computational intelligence, 2018, 2 (1): 41 - 50.

[2] Dong S. Xia Y. Peng T. Network abnormal traffic detection model based on semi-supervised deep reinforcement learning. IEEE Transactions on Network and Service Management, 2021, 18 (4): 4197 - 4212.

[3] Vinayakumar R. Soman K.P. Poornachandran P. Detecting malicious domain names using deep learning approaches at scale. Journal of Intelligent & Fuzzy Systems, 2018, 34 (3): 1355 - 1367.

[4] Chen G. Anomaly traffic detection method based on transfer learning of MobileNet-V2. Ship electronic engineering, 2024, 44 (02): 133 - 137.

[5] Shang F.J. Li S.S. Wang Y. et al. Traffic classification method based on dynamic balance adaptive transfer learning. Journal of Electronics and Information, 2022, 44 (09): 3308 - 3319.

[6] Zhang S.R. Chen B. Bu Y.J. et al. Encryption malicious traffic detection method based on transfer learning. Computer engineering and applications, 2022, 58 (17): 130 - 138.

[7] Huang Z.Y. Yang Y.G. Lei Z.C. Application of VAE oversampling and transfer learning in network intrusion detection. Computer age, 2021, (07): 50 - 54.

[8] Shen R.L. Pan W.M. Zhang H.J. Microblogging rumor detection method based on transfer learning. Computer engineering and design, 2021, 42 (12): 3534 - 3539.

[9] Ma H.Y. Bidirectional authentication of network identity based on transfer learning. Microcomputer application, 2022, 38 (09): 163 - 165.

[10] Wu Y.L. Zhang Z. Li T.Y. et al. Inter-site XSS intrusion detection method based on transfer learning. Science and technology information, 2023, 21 (19): 39 - 42.

[11] Wu P. Guo H. Buckland R. A transfer learning approach for network intrusion detection. IEEE 4th international conference on big data analytics (ICBDA). IEEE, 2019: 281 - 285.

[12] Zhao F. Zhao H. Chang Z.B. Small sample malicious domain name detection based on transfer learning. Computer engineering and design, 2022, 43 (12): 3381 - 3387.