Hadoop 환경의 기계 학습을 이용한 HTTP 공격 탐지 모델
HTTP Intrusion Detection Model Using Machine Learning in Hadoop Environment
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
모바일 시대가 된 이후 인터넷 트래픽 사용량은 기하급수적으로 증가 하고 있으며 이를 통한 각종 침해 사고와 비정상 트래픽이 급증하고 있다. 최근의 침해 사고는 보다 다양화 되고 지능적이며 복합적인 형태로 발생되고 있으며 이를 탐지하기 위해서는 기존의 방법들 이외에 다양한 방법이 요구 되고 있다. 이에 본 연구에서는 HTTP 서비스 트래픽을 빅 데이터로 수집하여 Web 서비스 침해 시도를 탐지하기 위한 방안으로 기계학습 기반의 지도 학습인 SVM과 의사결정 트리를 이용해 구현하여 검증해 보고 지도 학습의 한계를 보완하기 위해 패턴을 사용하지 않는 비지도 학습 기반의 Word to Vector 방식을 적용 할 수 있는 방안에 대해서 연구하고자 한다.
Abstract
Since the mobile era, Internet traffic usage has been increasing exponentially, and through this, various intrusion accidents and abnormal traffic are increasing rapidly. Recently, infringement accidents are occurring in a more diversified, intelligent and complex form, and various methods other than the existing methods are required to detect them. Therefore, in this study, a method to detect web service intrusion attempts by collecting HTTP service traffic as big data is implemented and verified using SVM and decision tree, which is a machine learning-based supervised learning without using patterns. In order to compensate for the limitations, I would like to study how to apply the Word to Vector method based on unsupervised learning.
참고문헌 (18)
- Dragos Gravrilut, "Malware Detection Using Perceptrons and Support Vector Machinesg", 2009 Computation World : Future Computing, Service Computation, Congnitive, Adaptive, Content, Patterns, pp.283~288 (2009)
- Chan Kyou Hwang, "Design of Implementation on real-time Anomaly Traffic Lookup &Analysis System", The Committe on Korean Network Operations and Management Review, 10(1), pp.43~55 (2007)
- Wonchul Kang, "A Hadoop-based Traffic Analysis System Architecture for Multiple Users", Proceedings of the Korean Information Science Society Conference, 38(1), pp.252~255 (2011)
- Taeshik Shon, "A hybrid machine learning approach to network anomaly detection", Information Sciences Journals, 177(18), pp.3799~3821 (2007)
- Jesus Mena, "Machine Learning Forensics for Law Enforcement, Security and Intelligence" (2011), CRC Press
- Steven Bird, "Natural Language Processing with Python" (2009), O`Reilly Media Inc
- 정해덕, "개선된 ATMSim을 이용한 DDoS 공격 분석", 인터넷정보학회논문지, 17(2), pp.19~28 (2016), 한국인터넷정보학회
- Andreas Muller, "Introduction to Machine Learning with Python" (2016), O`Reilly Media Inc
- 이진욱, "감성분석과 Word2vec을 이용한 비정형 품질 데이터 분석", 품질경영학회지, 45(1), pp.117~128 (2017), 한국품질경영학회[DOI]
- Hadi Pouransari, "Deep learning for sentiment analysis of movie reviews" (2019), Stanford University
- Gajanan Shinje, "Analysis of SQL Injection Using DVWA Tool", Annals of Computer Science and Information Systems, 10, pp.107~110 (2017)
- "word2vec" (2019)[URL]
- "Attack payload" (2020)[URL]
- Yousef Bakhdlaghi, "Snort and SSL", TLS Inspection, 2017
- Dharmaraj R. Patil, "Feature-based Malicious URL and Attack Type Detection Using Multi-class Classification", The ISC International Journal of Information Security, 10(2), pp.141~162 (2018)
- WENCHUAN YANG, "Detecting Malicious URLs via a Keyword-Based Convolutional Gated-Recurrent-Unit Neural Network", IEEE Access, 7, pp.29891~29900 (2019)
- Mohammad Almseidin, "Evaluation of Machine Learning Algorithms for Intrusion Detection System", IEEE 15th International Symposium on Intelligent Systems and Informatics (SISY), pp.277~282 (2017)
- Yao Pan, "Detecting web attacks with end-to-end deep learning", Journal of Internet Services and Applications, 10 (2019)