BROWSE
Detail
Journal Article
SITRAN: Self-Supervised IDS With Transferable Techniques for 5G Industrial Environments
- Authors
- Hyunjin Kim, Jonghoon Lee, Jong-Geun Park
- Issue Date
- 2024-11
- Citation
- IEEE Internet of Things Journal, v.11, no.21, pp.35465-35476
- ISSN
- 2327-4662
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Language
- English
- Type
- Journal Article
- Abstract
- The evolution of 5G mobile communication technology in use for over four years has rapidly increased the global subscriber base. This technological progress extends beyond broadcasting and mobile communications to various industries, particularly through the integration of 5G into smart factories. This integration has shifted the traditional production paradigm from the mass production to customized production systems that meet the individual customer demands. However, the digitization of smart factories has expanded their attack surfaces, making them potential targets for the cyber threats. Despite the development of various security solutions, threats are becoming increasingly sophisticated, necessitating research into artificial intelligence (AI)-based threat detection technologies. AI-based threat detection in real-world scenarios faces challenges in collecting sufficient data sets and deploying detection models in resource-constrained environments. Therefore, we propose a self-supervised learning-based network intrusion detection system (NIDS) that reduces reliance on the labeled data and utilizes the lightweight models for the deployment through the knowledge distillation techniques. Our system achieves continuous learning by transferring knowledge between the teacher and student models. To validate its efficiency and applicability, experiments were conducted using the simulated hacking data sets collected from a 5G smart factory testbed and evaluated using the standard benchmark data sets. The results demonstrate the effectiveness of the proposed system in smart factory environments compared to the existing approaches. This article contributes to the development of lightweight intrusion detection systems for deployment on the small-scale devices and provides insights into addressing the challenges of AI-based threat detection in 5G environments.
- KSP Keywords
- 5G mobile communication, Attack Surface, Benchmark data, Continuous learning, Cyber threats, Data sets, Detection Systems(IDS), Existing Approaches, Factory environment, Industrial environment, Its efficiency
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
