적대세력 외부망 활동 탐지를 위한 머신러닝 모델 연구
Researching machine learning models for detecting adversarial external network activity
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
기술의 발달로 매일 수백만건의 사이버공격이 실행되고 있으며, 매년 수백억개의 네트워크 트래픽이 발생한다. 공격자의 위치와 공격자가 사용한 중간경로를 파악하기 위해서는 해당 공격이 지나온 네트워크 경로를 파악하는 것이필수적이다. 본 연구에서는 Oregon Route Views Project, RIPE NCC public Archive와 같은 공개된 저장소에서 BGP 데이터를 수집하고 분석하여 적대적인세력의 외부망 활동을 탐지한다. 추가적으로 전처리된 BGP 데이터를 사용하여다출처에서 수집한 데이터와 결합하여 데이터 분석을 진행한다. 여러 개의머신러닝 모델을 사용하여 실험을 진행하며, 다양한 지표를 사용하여 모델의성능을 비교한다. 이와 같은 연구를 통해 이상 데이터를 탐지하고 중간 경로를파악하여 공격을 차단하고 추가적인 공세적 및 방어적 대응이 가능할 것이다.
Abstract
With the advancement of technology, millions of cyberattacks are launched every day, generating tens of billions of kilobytes of network traffic every year. In order to determine the location of the attacker and the intermediate routes used by the attacker, it is essential to understand the network routes traversed by the attack. In this research, we collect and analyze BGP data from public repositories such as Oregon Route Views Project and RIPE NCC public Archive to detect external network activities of hostile actors. Furthermore, we use preprocessed BGP data and combine it with data collected from multiple sources for data analysis. Experiments are conducted using multiple machine learning models and the performance of the models is compared using various metrics. This research will help detect anomalous data and identify intermediate paths to block attacks and enable additional offensive and defensive responses.
참고문헌 (14)
- "Cisco Annual Internet Report(2018-2023) White Report"[URL]
- "check point: research cyber attacks increased 50% year over year"[URL]
- Al-Musawi, Branch Philip, "Bgp Anomaly Detection Techniques : A Survey", IEEE Communications Surveys & Tutorials, 19(1), pp.377~396 (2016)
- C. Yang, "Bgp Anomaly Detection-a Path-Based Apporach", Paper presented at the 2023 3rd Asia-Pacific Conference on Communications Technology and Computer Science (ACCTCS) (2023)
- N. M. Al-Rousan, "Machine Learning Models for Classification of Bgp Anomalies", Paper presented at the 2012 IEEE 13th International Conference on High Performance Switching and Routin (2012)
- X. Dai, "Application of Machine Learning in Bgp Anomaly Detection", Paper presented at the Journal of Physics : Conference Series (2019)
- M. Cheng, "Ms-Lstm : A Multi-Scale Lstm Model for Bgp Anomaly Detection", Paper presented at the 2016 IEEE 24th International Conference on Network Protocols (ICNP) (2016)
- K. Hoarau, "Bgnn : Detection of Bgp Anomalies Using Graph Neural Networks", Paper presented at the 2022 IEEE Symposium on Computers and Communications (ISCC) (2022)
- M. Jiang, "Weakly Supervised Anomaly Detection: A Survey", arXiv preprint arXiv:2302.04549, ~ (2023)
- K. McGlynn, "Detecting Bgp Route Anomalies with Deep Learning", Paper presented at the IEEE INFOCOM 2019-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) (2019)
- A. H. Muosa, "Internet Routing Anomaly Detection Using Lstm Based Autoencoder", Paper presented at the 2022 International Conference on Computer Science and Software Engineering (CSASE) (2022)
- Q. P. Nguyen, "Gee : A Gradient-Based Explainable Variational Autoencoder for Network Anomaly Detection", Paper presented at the 2019 IEEE Conference on Communications and Network Security (CNS) (2019)
- O. R. Sanchez, "Comparing Machine Learning Algorithms for Bgp Anomaly Detection Using Graph Features", Paper presented at the Proceedings of the 3rd ACM CoNEXT Workshop on Big DAta, Machine Learning and Artificial Intelligence for Data Communication Networks (2019)
- 박한솔, "오토인코더 기반의 외부망 적대적 사이버 활동 징후 감지", 인터넷정보학회논문지, 23(6), pp.39~48 (2022), 한국인터넷정보학회