题名

一個有效的深度學習超參數選擇方法應用於入侵偵測系統

并列篇名

An Effective Hyperparameter Selection for Deep Learning Algorithm in Intrusion Detection System

作者

張維晏(Wei-Yan Chang)；陳羿霖(Yi-Lin Chen)；陳煥(Huang Chen)；蔡崇煒(Chun-Wei Tsai)

关键词

入侵偵測系統 ； 深度學習 ； 超啟發式演算法 ； 超參數 ； Intrusion detection system ； deep learning ； metaheuristic algorithm ； hyperparameters

期刊名称

資訊安全通訊

卷期/出版年月

26卷4期（2020 / 12 / 01）

页次

1 - 16

内容语文

繁體中文
中文摘要

許多近期的研究利用機器學習或深度學習方法，作為入侵偵測系統的判別模組方法。部分研究主要注重於如何改良深度學習架構，來提升深度學習的準確率。其中一個影響深度學習的效能的原因是超參數的設定，包含了神經元的個數、層數或學習率等。然而目前超參數的設定，通常是依據個人的經驗或窮舉法方式來設定超參數的數值。在本論文中將差分進化演算法與深度學習結合，提出了一種可以自適應調整超參數的方法，並將其應用於入侵偵測系統中。本論文將所提出的方法與其他機器學習和深度學習進行比較。最終實驗結果說明，本論文所提的超啟發式演算法，在較複雜的入侵偵測問題上，可以有效的找到深度學習的最佳超參數，能有效提升深度學習模型對於入侵攻擊的檢測能力。
英文摘要

With the great success of artificial intelligence, machine learning and deep learning have been applied to intrusion detection as the core methods in recent years. The primary focus of many researches is on how to improve the performance by tuning the deep learning model and the associated hyperparameters. Hyperparameters are critical factors for deep learning-based method which includes how many layers should be used in the model; how many neurons are there for each layer; and how to set up the learning rate properly. However, most of studies set the hyperparameters depending on personal experience or using inefficient brute force exhaustive search. In this paper, we will present a self-adaptive method to decide the setting of hyperparameters that integrated deep learning and differential evolution. The proposed scheme is then be used for intrusion detection system. To evaluate the effectiveness of the proposed method, the performance of the scheme is compared to those of other machine learning and deep learning methods. Three performance metrics in terms of accuracy, recall and precision are used. Results show that the proposed algorithm can find the best hyperparameters setting for deep learning model than other methods compared in this paper.
主题分类 基礎與應用科學 > 資訊科學
参考文献
  1. Chen, Z. H.,Chen, Y. L.,Chang, W. Y.,Tsai, C. W.(2019).A Hybrid Classification Algorithm for Intrusion Detection System.Communications of the CCISA,25(1),14-27.
    連結：
  2. Alaba, F. A.,Othman, M.,Hashem, I. A. T.,Alotaibi, F.(2017).Internet of Things Security: A Survey.Journal of Network and Computer Applications,88,10-28.
  3. Bridges, S. M.,Vaughn, R. B.(2000).Intrusion Detection via Fuzzy Data Mining.Proceedings of the Annual Canadian Information Technology Security Symposium
  4. A. Burt and T. Pott, “Gitpaste-12: A New Worming Botnet with Reverse Shell Capability Spreading via GitHub and Pastebin, 2020, https://blogs.juniper.net/en-us/threat-research/gitpaste-12 (2021/01/14).
  5. Cortes, C.,Vapnik, V.(1995).Support Vector Networks.Machine Learning.,20,273-297.
  6. Duy, P. H.,Diep, N. N.(2017).Intrusion Detection Using Deep Neural Network.SoutheastAsian Journal Sciences,5(2),111-125.
  7. Farahnakian, F.,Heikkonen, J.(2018).A Deep Auto-encoder based Approach for Intrusion Detection System.Proceedings of the International Conference on Advanced Communication Technology
  8. Giacinto, G.,Perdisci, R.(2008).Intrusion detection in computer networks by a modular ensemble of one-class classifiers.Information Fusion,9(1),69-82.
  9. Gilchrist, A.(2016).Industry 4.0: The Industrial Internet of Things.New York:Springer.
  10. Goodfellow, I.,Bengio, Y.,Courville, A.(2016).Deep Learning.United States:The MIT Press.
  11. Hand, D.,Yu, K.(2007).Idiot’s Bayes: Not So Stupid after All?.International StatisticalReview,69(3),385-398.
  12. Hochreiter, S. ,Schmidhuber, J.(1997).Long Short-Term Memory.Neural Computation,9,1735-1780.
  13. Kang, D.,Fuller, D.,Honavar, V.(2005).Learning classifiers for misuse and anomaly detection using a bag of system calls representation.Proceedings from the Sixth Annual IEEE SMC Information Assurance Workshop
  14. Keller, J. M.,Gray, M. R.,Givens, J. A.(1985).A Fuzzy K-nearest Neighbor Algorithm.IEEE Transactions on System, Man, Cybernetics,15(4),580-585.
  15. Kim, J.,Kim, J.,Thu, H. L. T.,Kim, H.(2016).Long Short Term Memory Recurrent Neural Network Classifier for Intrusion Detection.Proceedings of the International Conference on Platform Technology and Service
  16. R. M. Lee, M. J. Assante and T. Conway, “Analysis of the Cyber Attack on the Ukrainian Power Grid: Defense Use Case., 2016, https://ics.sans.org/media/E-ISAC_SANS_Ukraine_DUC_5.pdf (2021/01/14).
  17. Lee, W. P.,Chien, W. J.(2011).A Novel Differential Evolution with Co-evolution Strategy.Journal of Computers,6(3),594-602.
  18. Li, Y.,Xia, J.,Zhang, S.,Yan, J.,Ai, X.,Dai, K.(2012).An Efficient Intrusion Detection System based on Support Vector Machines and Gradually Feature Removal Method.Expert Systems with Applications,39(1),424-430.
  19. Liao, H. J,Lin, C. H. R.,Lin, Y. C.,Tung, K. Y.(2013).Intrusion Detection System: A Comprehensive Review.Journal Network Computer Applications,36(1),16-24.
  20. Liaw, A.,Wiener, M.(2002).Classification and Regression by Random Forest.R News,2(3),18-22.
  21. Mukkamala, S.,Sung, A. H.,Abraham, A.(2005).Intrusion detection using an ensemble of intelligent paradigms.Journal Network and Computer Applications,28(2),167-182.
  22. Quinlan, J. R.(1986).Induction of Decision Trees.Machine Learning,1(1),81-106.
  23. Redstonewill.Redstonewill, “Cross Entropy.” 2020..
  24. Shon, T.,Moon, J.(2007).A Hybrid Machine Learning Approach to Network Anomaly Detection.Information Sciences,177(18),3799-3821.
  25. Shone, N.,Ngoc, T. N.,Phai, V. D.,Shi, Q.(2018).A Deep Learning Approach to Network Intrusion Detection.IEEE Transactions on Emerging Topics in Computational Intelligence,2(1),41-50.
  26. Storn, R.,Price, K.(1997).Differential Evolution - A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces.Journal of Global Optimization,11,341-359.
  27. Tang, T. A.,Mhamdi, L.,McLernon, D.,Zaidi, S. A. R.,Ghogho, M.(2016).Deep Learning Approach for Network Intrusion Detection in Software Defined Networking.Proceedings of the International Conference on Wireless Networks and Mobile Communications
  28. Tian, Z.,Fong, S.(2016).Survey of Meta-Heuristic Algorithms for Deep Learning Training.Optimization Algorithms—Methods and Applications, IntechOpen
  29. Tsai, C. F.,Hsu, Y. F.,Lin, C. Y.,Lin, W. Y.(2009).Intrusion Detection by Machine Learning: A Review.Expert Systems with Applications,36(10),11994-12000.
  30. Tuba, E.,Tuba, M.,Simian, D.(2016).Adjusted Bat Algorithm for Tuning of Support Vector Machine Parameters.Proceedings of the IEEE Congress on Evolutionary Computation
  31. University of New Brunswick, NSL-KDD dataset, https://www.unb.ca/cic/datasets/nsl.html (2021/01/18)
  32. Yang, X. S.,Deb, S.,Fong, S.(2011).Accelerated Particle Swarm Optimization and Support Vector Machine for Business Optimization and Applications.Proceedings of the International Conference on Networked Digital Technologies
  33. Yin, C.,Zhu, Y.,Fei, J,He, X.(2017).A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks.IEEE Access,5,21954-21961.
  34. Young, S. R.,Rose, D. C.,Karnowski, T. P.,Lim, S. H.,Patton, R. M.(2015).Optimizing Deep Learning Hyper-Parameters through An Evolutionary Algorithm.Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments
print cancel