본문 바로가기
KERD
논문KCI 등재

딥뉴럴네트워크 기반의 네트워크 침입탐지시스템 설계

A Design of Deep Neural network-based Network Intrusion Detection System

박기웅|권현|방승호
한국차세대컴퓨팅학회 (KINGComputing)|2020.02|한국차세대컴퓨팅학회 논문지 (The Journal of Korean Institute of Next Generation Computing)|제16권 제1호|pp. 7-18|DOI 10.23019/kingpc.16.1.202002.001

2

조회

0

다운로드

5

인용

0

참고문헌

키워드

기계학습Machine learning침입탐지시스템Deep neural network딥뉴럴네트워크KDD CUP 99Intrusion detection system
주제분류컴퓨터학

초록

최근 들어, 딥뉴럴네트워크는 이미지 인식, 패턴 분석, 침입탐지 등 다양한 분야에 활용되고 있다. 본 논문에서는 딥뉴럴네트워크 기반의 침입탐지방법에 대하여 여러 가지 파라미터를 조절하여 탐지 성공률을 실험적으로 분석하였다. 대표적인 침입 데이터인 KDD CUP 99 데이터셋을 사용하였으며, 텐서플로우 머신러닝 라이브러리를 이용하였고 각 파라미터를 수정하여 탐지율을 측정하였다. 추가적으로 선형회귀(linear regression, LR), 나이브 베이즈 분류 (naive bayes classification, NB), 최근접 이웃(k-nearest neighbors, KNN), 의사결정트리(decision tree, DT), 랜덤 포레스트(random forest, RF) 등의 방법들에 대해서도 실험적으로 비교 분석하였다. 각 파라미터로는 각 층의 노드 수, Dropout의 수, 활성화 함수 등을 고려하여 분석하였으며, 은닉층이 5개인 딥뉴럴네트워크 일 때, 93.8% 탐지 정확도로 가장 높은 것을 확인할 수 있었다.

Abstract

Recently, deep neural networks (DNNs) provide the good performance for image recognition, pattern analysis and intrusion detection. In this paper, we analyzed experimentally the success rate of detection by manipulating various parameters for intrusion detection method of deep neural network. We used the KDD CUP 99 data set, which is a widely used intrusion data, and modified each parameter using the TensorFlow machine learning library to measure the detection accuracy. We also analyzed linear regression (LR), naive bayes classification (NB), k-nearest neighbors (KNN), decision trees (DT) and random forests. (random forest, RF). We analyzed the parameters by modifying the number of nodes in each layer, the number of dropouts, and the activation function. Experimental results show that DNNS has the highest detection with 93.8% accuracy with 5 hidden layers.

참고문헌 (36)

  1. Tidjon, Lionel N., "Intrusion Detection Systems: A Cross-Domain Overview", IEEE Communications Surveys & Tutorials (2019)
  2. Mawla, Tanjila, "Emerging Technologies in Data Mining and Information Security", pp.645~655 (2019), Springer
  3. Alhakami, Wajdi, "Network Anomaly Intrusion Detection Using a Nonparametric Bayesian Approach and Feature Selection", IEEE Access, 7, pp.52181~52190 (2019)
  4. Schmidhuber, Jürgen, "Deep learning in neural networks: An overview", Neural networks, 61, pp.85~117 (2015)
  5. Gao, Shangqi, "Multi-scale deep neural networks for real image superresolution", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2019)
  6. Huang, Kun-Yi, "Speech Emotion Recognition Using Deep Neural Network Considering Verbal and Nonverbal Speech Sounds", ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2019)
  7. Akhundov, Riad, "Development of a deep neural network for automated electromyographic pattern classification", Journal of Experimental Biology, 222(5), pp.jeb198101~ (2019)
  8. Tavallaee, Mahbod, "A detailed analysis of the KDD CUP 99 data set", 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications. IEEE (2009)
  9. Wang, HaiYing, "Information-based optimal subdata selection for big data linear regression", Journal of the American Statistical Association, 114(525), pp.393~405 (2019)
  10. Chen, Jiangning, "Naive Bayes with Correlation Factor for Text Classification Problem", arXiv preprint arXiv:1905.06115, ~ (2019)
  11. Zheng, Wei, "An Improved k-Nearest Neighbor Classification Algorithm Using Shared Nearest Neighbor Similarity", Metallurgical & Mining Industry, 10 (2015)
  12. Song, Yan-Yan, "Decision tree methods : applications for classification and prediction", Shanghai archives of psychiatry, 27(2), pp.130~ (2015)
  13. Farnaaz, Nabila, "Random forest modeling for network intrusion detection system", Procedia Computer Science, 89, pp.213~217 (2016)
  15. Kwon, Hyun, "Optimal Cluster Expansion-Based Intrusion Tolerant System to Prevent Denial of Service Attacks", Applied Sciences, 7(11), pp.1186.2~ (2017)
  16. KBennett, Kristin P., "Advances in Neural Information processing systems" (1999)
  17. 신동혁, "K-평균 클러스터링을 이용한 네트워크 유해트래픽 탐지", 한국통신학회논문지, 41(2), pp.277~284 (2016), 한국통신학회
  18. M. Tahir, "Hybrid machine learning technique for intrusion detection system", 5th International Conference on Computing and Informatics (ICOCI) (2015)
  19. N. Gao, "Wang An Intrusion Detection Model Based on Deep Belief Networks, Advanced Cloud and Big Data (CBD)", 2014 Second International Conference on, pp.247~252 (2014)
  20. 조성래, "SVM과 인공 신경망을 이용한 침입탐지 효과 비교 연구", 한국산학기술학회논문지, 17(2), pp.703~711 (2016), 한국산학기술학회[DOI]
  21. Kim, Kwangjo, "Network Intrusion Detection Using Deep Learning: A Feature Learning Approach" (2018), Springer
  22. Mathai, K. James, "Performance Comparison of Intrusion Detection System Between Deep Belief Network (DBN) Algorithm and State Preserving Extreme Learning Machine (SPELM)Algorithm", 2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT). IEEE (2019)
  23. Aggarwal, Preeti, "Contribution of four class labeled attributes of kdd dataset on detection and false alarm rate for intrusion detection system", Indian Journal of Science and Technology, 9(5), pp.1~8 (2016)
  24. Gurung, Sandeep, "Deep learning approach on network intrusion detection system using NSL-KDD dataset", International Journal of Computer Network and Information Security (IJCNIS), 11(3), pp.8~14 (2019)
  25. Özgür, Atilla, "A review of KDD99 dataset usage in intrusion detection and machine learning between 2010 and 2015", PeerJ Preprints, 4(1), pp.e1954v1~ (2016)
  26. Meena, Gaurav, "A review paper on IDS classification using KDD 99 and NSL KDD dataset in WEKA", 2017International Conference on Computer, Communications and Electronics (Comptelix). IEEE (2017)
  27. O. AI-Jarrah, "Network intrusion detection system using neural network classification of attack behavior", Journal of Advances in Information Technology, 6(1) (2015)
  28. Li, Yuanzhi, "Advances in Neural Information Processing Systems" (2017)
  29. 와셈 울라, "Crowd Behavior Detection using Convolutional Neural Network", 한국차세대컴퓨팅학회 논문지, 15(6), pp.7~14 (2019), 한국차세대컴퓨팅학회[DOI]
  30. 알아나지라얀, "Artificial Intelligence based framework for efficient management of resources in data centers", 한국차세대컴퓨팅학회 논문지, 15(2), pp.79~88 (2019), 한국차세대컴퓨팅학회[DOI]
  31. 김준태, "드라이빙 게임 환경에서의 효과적인 학습 데이터 수집 및 컨볼루셔널 뉴럴 네트워크 기반의 자율주행", 한국차세대컴퓨팅학회 논문지, 15(1), pp.28~37 (2019), 한국차세대컴퓨팅학회
  32. Vigneswaran, K. Rahul, "Evaluating shallow and deep neural networks for network intrusion detection systems in cyber security", 2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT). IEEE (2018)
  33. Yin, Xinyou, "A flexible sigmoid function of determinate growth", Annals of botany, 91(3), pp.361~371 (2003)
  34. Bottou, Léon, "Large-scale machine learning with stochastic gradient descent", Proceedings of COMPSTAT'2010, pp.177~186 (2010), Physica-Verlag HD
  35. Kingma, Diederik P., "Adam:A method for stochastic optimization", arXiv preprint arXiv:1412.6980, ~ (2014)
  36. Abadi, Martín, "Tensorflow: A system for large-scale machine learning", 12th {USENIX}Symposium on Operating Systems Design and Implementation ({OSDI} 16) (2016)

이 간행물의 다른 논문 (7건)

각속도 센서를 이용한 걸음 검출 및 보폭 추정 방법변재영, 이정훈, 강희선, 이태원pp. 19-293차원 수술 항법 장치를 위한 정밀 얼굴 정합이정진, 박태용, 강승우, 김현준pp. 30-42밝기와 노이즈 관계의 확률적 선험정보를 이용한 노이즈 제거황영배pp. 43-55클라우드 서비스를 이용한 클라우드 솔루션 및 서비스 대상 보안 취약점 점검 결과 및 보안수준 향상방안정현철, 민영기, 정기봉, 서보국, 김종철pp. 56-64프라이빗 블록체인 기반 효율적 합의 알고리즘 선정을 위한 성능평가요소 연구민연아pp. 65-74
원문 보기