XAI 기반 Network 침입공격 탐지 및 공격유형별 대표적 특징분석에 관한 연구
A Study on Network Intrusion Attack Detection and Analysis of Representative Features by Attack Type
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
오늘날 다양한 네트워크 시스템이 연계되어 상용화가 이루어짐에 따라 사이버 보안의 중요성이 더욱 강조된다. 그중 IDS(Intrusion Detection System)는 사이버 보안 영역 내에 존재하는 네트워크 보안 분야에서 중요한 역할을 한다. 빅데이터 시대를 맞이하여 방대한 데이터 내에 존재하는 침입 행위를 빠르고 정확하게 탐지하는 것이 가장 중요하다. 분석가들은 이러한 침입 행위 탐지를 위하여 AI를 도입하여 탐지율을 높이고 알려지지 않은 공격 행위를 탐지하는 연구에 집중해왔다. 하지만 AI의 판단만을 근거로 탐지 결과를 신뢰할 수 없다. 이를 해결하기 위해 도입된 개념이 XAI(eXplainable Artificial Intelligence)로 불리우는 설명 가능한 AI이다. 본 논문은 XAI 중 하나인 SHAP을 활용하여 분류된 레이블 별 중요하게 작용하는 feature를 선정하여 레이블을 설명하고자 한다.
Abstract
Today, the importance of cybersecurity is further emphasized as various network systems are linked and commercialized. Among them, IDS plays an important role in the field of network security that exists within the cybersecurity area. In the era of big data, it is most important to quickly and accurately detect intrusion behavior that exists within massive data. Analysts have been focusing on research to increase the detection rate and detect unknown attack behaviors by introducing AI to detect such intrusive behaviors. However, the detection results cannot be trusted based solely on AI’s judgment. The concept introduced to solve this problem is an explainable AI called XAI. This paper intends to explain the Label by selecting important features for each classified Label using SHAP, one of the XAI.
참고문헌 (10)
- Depren, O., "An intelligent intrusion detection system for anomaly and misuse detection in computer networks", Expert Systems with Applications, 29(4), pp.713~722 (2005)
- J. Jabez, "Intrusion Detection System (IDS): anomaly detection using outlier detection approach", Procedia Comput. Sci, 48(3), pp.338~346 (2015)
- Tongtong Su, "BAT: Deep Learning Methods on Network Intrusion Detection Using NSL-KDD Dataset", IEEE Access, 8, pp.29575~29585 (2020), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- L. Dhanabal, "A Study on NSL KDD Dataset for Intrusion Detection System based on Classification Algorithms", International Journal of Advanced Research in Computer and Communication Engineering, 4(6), pp.446~452 (2015)
- S. Lakhina, "Feature reduction using principal component analysis for effective anomaly–based intrusion detection on NSL-KDD", Int. J. Eng. Sci. Technol, 2(6), pp.1790~1799 (2010)
- S. Revathi, "A Detailed Analysis on NSL-KDD Dataset Using Various Machine Learning Techniques for Intrusion Detection", International Journal of Engineering Research & Technology, 2(12), pp.1848~1853 (2013)
- S. Mane, "Explaining network intrusion detection system using explainable ai framework", arXiv preprint arXiv:2103.07110, ~ (2021)
- A. B. Parsa, "Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis, Accident Anal", Prevention, 136, pp.105405~ (2020)
- S. Wali, "Explainable AI and Random Forest Based Reliable Intrusion Detection system", TechRxiv, ~ (2021)
- Ł. Wawrowski, "Detectiong anomalies and attacks in network traffic monitoring with classification methods and XAI-based explainability", procedia computer science, 192, pp.2259~2268 (2021)