상세정보
학술대회
Network Flow Data Re-collecting Approach Using 5G Testbed for Labeled Dataset
- 발행일
- 202102
- 출처
- International Conference on Advanced Communications Technology (ICACT) 2021, pp.254-258
- 협약과제
- 21HR2400, 5G＋ 서비스 안정성 보장을 위한 엣지 시큐리티 기술 개발, 박종근
- 초록
- With the emergence of fifth generation technology (5G) environments, intelligent network security against constantly evolving attacks related to massive Internet of Things devices, user equipment, and various edge services has become more important. Moreover, to employ state-of-The-Art learning-based detection methodologies, a labeled dataset is essential. However, it is not easy to obtain such a dataset by collecting the real communication dataset for a 5G network. Hence, in this study, we build a purpose-built 5G testbed that can observe 5G network features by replaying the collected data. Additionally, we implement a specialized network collector system that can 5G edge network. Subsequently, the network traffic data collected in the configured 5G testbed are analyzed. It is discovered that a re-collecting methodology using the proposed 5G testbed and network collector can be sufficiently utilized to construct a 5G-based labeled dataset for supervised learning methods.
- KSP 제안 키워드
- 5G Network, Collector system, Data collected, Edge network, Edge services, Fifth Generation(5G), Flow Data, Generation technology, Internet of thing(IoT), Learning methods, Learning-based