5G 모바일 에지 컴퓨팅에서 빅데이터 분석 기능에 대한 데이터 오염 공격 탐지 성능 향상을 위한 연구
A Study on Improving Data Poisoning Attack Detection against Network Data Analytics Function in 5G Mobile Edge Computing
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
5G 네트워크의 핵심 기술로 모바일 에지 컴퓨팅(Mobile Edge Computing, MEC)이 주목받음에 따라, 모바일 사용자의 데이터를 기반으로 한 5G 네트워크 기반 에지 AI 기술이 최근 다양한 분야에서 이용되고 있다. 하지만, 전통적인 인공지능 보안에서와 마찬가지로, 에지 AI 핵심 기능을 담당하는 코어망 내 표준 5G 네트워크 기능들에 대한 적대적 교란이 발생할 가능성이 존재한다. 더불어, 3GPP에서 정의한 5G 표준 내 Standalone 모드의 MEC 환경에서 발생할 수 있는 데이터 오염 공격은 기존 LTE망 대비 현재 연구가 미비한 실정이다. 본 연구에서는 5G에서 에지 AI의 핵심 기능을 담당하는 네트워크 기능인 NWDAF를 활용하는 MEC 환경에 대한 위협 모델을 탐구하고, 일부 개념 증명으로써 Leaf NWDAF에 대한 데이터 오염 공격 탐지 성능을 향상시키기 위한 특징 선택 방법을 제안한다. 제안한 방법론을 통해, NWDAF에서의 Slowloris 공격 기반 데이터 오염 공격에 대해 최대 94.9%의 탐지율을 달성하였다.
Abstract
As mobile edge computing (MEC) is gaining attention as a core technology of 5G networks, edge AI technology of 5G network environment based on mobile user data is recently being used in various fields. However, as in traditional AI security, there is a possibility of adversarial interference of standard 5G network functions within the core network responsible for edge AI core functions. In addition, research on data poisoning attacks that can occur in the MEC environment of standalone mode defined in 5G standards by 3GPP is currently insufficient compared to existing LTE networks. In this study, we explore the threat model for the MEC environment using NWDAF, a network function that is responsible for the core function of edge AI in 5G, and propose a feature selection method to improve the performance of detecting data poisoning attacks for Leaf NWDAF as some proof of concept. Through the proposed methodology, we achieved a maximum detection rate of 94.9% for Slowloris attack-based data poisoning attacks in NWDAF.
참고문헌 (21)
- A. C. Chen Liu, "Traffic Safety System Edge AI Computing", 2021 IEEE, 2021, 01~02
- S.W.Hong, "Technologies of Intelligence Edge Computing and Networking", Electronics and Telecommunications Trends, 34(1), pp.23~35 (2019)
- M. K. Shin, "Development of Network Data Analytics Function(NWDAF)and Intelligence Technology Standards for 5G Network Automation" (2021), Electronics and Telecommunications Research Institute
- 3GPP, "Release 16 Description; Summary of Rel-16 Work Items", TR 21.916, ~ (2020)
- S. -M. Senouci, "AI-Driven Cybersecurity Threats to Future Networks", IEEE Vehicular Technology Magazine, 15(3), pp.5~6 (2020)
- S. Hussain, "LTEInspector : A Systematic Approach for Adversarial Testing of 4G LTE", Network and Distributed Systems Security (NDSS) Symposium (2018)
- Chuan Yu, "Improving 4G", 5G air interface security : A survey of existing attacks on different LTE layers, j. comnet, pp.2021, 201(C)[DOI]
- H. Fang, "Machine Learning for Intelligent Authentication in 5G and Beyond Wireless Networks", IEEE Wireless Communications, 26(5), pp.55~61 (2019)
- C. Benzaïd, "AI for Beyond 5G Networks : A Cyber-Security Defense or Offense Enabler?", IEEE Network, 34(6), pp.140~147 (2020)
- Y. Jeon, "A Distributed NWDAF Architecture for Federated Learning in 5G", 2022 IEEE International Conference on Consumer Electronics (ICCE), pp.1~2 (2022)
- Sehan Samarakoon, "5G-NIDD : A Comprehensive Network Intrusion Detection Dataset Generated over 5G Wireless Network", IEEE Dataport, Dec (2022)
- 3GPP, "Architecture enhancements for 5G System (5GS) to support network data analytics services", TS 23.288, ~ (2021)
- 3GPP, "5G; 5G System; Network function repository services; Stage 3", TS 29. 510, ~ (2019)
- E. Yalin, "Shi, Adversarial Machine Learning for 5G Communications Security, IEEE Game Theory and Machine Learning for Cyber Security, pp", IEEE Game Theory and Machine Learning for Cyber Security, pp.270~288 (2021)
- D. Moustis, "Evaluating security controls against HTTP-based DDoS attacks", IISA 2013, pp.1~6 (2013)
- Y. Liu, "A Secure Federated Learning Framework for 5G Networks", IEEE Wireless Communications, 27(4), pp.24~31 (2020)
- S.Y.Lee, "Federated learning over private 5G networks: demo", Proceedings of the Twenty-Third International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc '22), pp.295~296 (2022), Association for Computing Machinery
- E. Piri, "5GTN : A Test Network for 5G Application Development and Testing", 2016 European Conference on Networks and Communications (EuCNC), pp.313~318 (2016)
- Girish Chandrashekar, "A survey on feature selection methods", Computers & Electrical Engineering, 40(1), pp.16~28 (2014)
- N. M. Tahir, "Feature Selection for Classification Using Decision Tree", 2006 4th Student Conference on Research and Development, pp.99~102 (2006)
- "Argus: System + Network Monitoring"[URL]