臺灣博碩士論文加值系統

身處在一個天天都會使用到網路的時代，網路安全成為了一項不可忽視的重要議題。網路帶給我們便利的同時，隱藏在背後的攻擊也隨之而來，偵測並預防各種攻擊手段成為網路安全的第一步。入侵偵測系統藉由監測網路或系統流量偵測出惡意攻擊，各種入侵偵測方法在近年被大量實驗並提出，但面對日新月異且不斷進步的攻擊手段時，許多方法因過時被淘汰，因此，找出一個完善的入侵偵測系統被認為是迫切需要解決的問題。在本論文中，我們使用量子啟發式演算法與深度學習技術中的深度神經網路對入侵偵測模型進行研究，為了降低模型的誤報率與提升準確率，我們使用量子啟發式演算法對入侵偵測資料集進行預處理，移除多餘且無用的特徵提升判斷攻擊的效能，接著再使用量子啟發式演算法調整深度神經網路的超參數，利用量子啟發式演算法尋找出的超參數最佳組合建構入侵偵測模型。實驗使用的入侵偵測資料集為加拿大網路安全局在2017年提出的CICIDS2017，藉由使用此資料集來確保我們的入侵偵測模型在抵禦符合當今時代背景的攻擊手段時的效能。實驗結果表明，使用量子啟發式演算法結合深度學型技術偵測入侵攻擊時有良好的準確率的同時也有相當低的誤報率。

In an era where the internet is used every day, internet security has become an important issue that cannot be ignored. While the internet brings us convenience, it also comes with hidden attacks. Detecting and preventing various attack methods is the first step in ensuring internet security. Intrusion Detection Systems (IDS) monitor network or system traffic to detect malicious attacks. In recent years, numerous intrusion detection methods have been extensively experimented with and proposed. However, many methods have become outdated and obsolete in the face of constantly evolving and advancing attack techniques. Therefore, finding a robust intrusion detection system is considered an urgent problem to solve.
In this paper, we conduct research on intrusion detection models using quantum-inspired algorithms and Deep Neural Networks (DNN), a technique in deep learning. To reduce the false positive rate and improve accuracy, we preprocess the intrusion detection dataset using quantum-inspired algorithms. This involves removing redundant and irrelevant features to enhance the performance of attack detection. We then utilize quantum-inspired algorithms to fine-tune the hyperparameters of the deep neural network. By leveraging the optimal combination of hyperparameters discovered by the quantum-inspired algorithms, we construct an intrusion detection model.
The experimental dataset used for intrusion detection is the CICIDS2017 dataset proposed by the Canadian Institute for Cybersecurity in 2017. By using this dataset, we ensure that our intrusion detection model performs well in defending against attack techniques relevant to the current era. The experimental results demonstrate that the combination of quantum-inspired algorithms and deep learning techniques achieves high accuracy in detecting intrusion attacks while maintaining a low false positive rate.

摘要 i
Abstract ii
目錄 iii
圖目錄 iv
表目錄 v
第一章前言 1
第二章文獻探討 4
第三章系統架構與方法 6
第四章實驗結果與比較 17
第五章結論 27
參考文獻 28

[1] F. A. Alaba, M. Othman, I. A. T. Hashem, and F. Alotaibi, “Internet of things security: a survey,” Journal of Network and Computer Applications, vol. 88, pp. 10-28, 2017.
[2] N. Marir, H. Wang, G. Feng, B. Li, and M. Jia, “Distributed abnormal behavior detecion approach based on deep belief network and ensemble svm using spark,” IEEE Access 6 (2018) 59657–59671.
[3] P. V. Amoli, and T. Hämäläinen , “A real time unsupervised NIDS for detecting unknown and encrypted network attacks in high speed network,” In Proceedings of the 2013 IEEE International Workshop on Measurements & Networking (M&N), Naples, Italy, 7–8 October 2013; pp. 149–154.
[4] Raghunath, B. Raman, and S.N. Mahadeo. "Network intrusion detection system (NIDS)." 2008 First International Conference on Emerging Trends in Engineering and Technology. IEEE, 2008.
[5] L. Deng, “A tutorial survey of architectures, algorithms, and applications for deep learning,” APSIPA Trans. Signal Inform. Process. 3 (2014).
[6] X. Du, Y. Cai, S. Wang, L. Zhang, “Overview of deep learning,” 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC), IEEE, 2016, pp. 159–164.
[7] L. Cervante, B. Xue, M. Zhang, and L. Shang, “Binary particle swarm optimisation for feature selection: A filter based approach,” 2012 IEEE Congress on Evolutionary Computation, IEEE, 2012, pp. 1–8.
[8] I. Ahmad, “Feature selection using particle swarm optimization in intrusion detection,” Int. J. Distrib. Sens. Netw. 11 (10) (2015) 806954.
[9] T. A. Tang, L. Mhamdi, D. McLernon, S.A.R. Zaidi, and M. Ghogho, “Deep learning approach for network intrusion detection in software defined networking,” in Proceedings of the International Conference on Wireless Networks and Mobile Communications, 2016, pp. 258-263.
[10] J. Kim, N. Shin, S. Y. Jo, and S. H. Kim, “Method of intrusion detection using deep neural network,” in Proc. IEEE Int. Conf. Big Data Smart Comput., Hong Kong, China, Feb. 2017, pp. 313–316.
[11] M. J. Kang and J. W. Kang, “Intrusion detection system using deep neural network for in-vehicle network security,” PLoS One, vol. 11, no. 6, Jun. 2016, Art. no. e0155781.
[12] W. Elmasry, A. Akbulut, and A. H. Zaim, “Evolving deep learning architectures for network intrusion detection using a double PSO metaheuristic,” Comput. Networks, vol. 168, pp.107402, February 2020.
[13] H. P. Chiang, Y. H. Chou, and C. H. Chiu, “A quantum-inspired tabu search algorithm for solving combinatorial optimization problems,” Soft Comput 18, 1771–1781 (2014).
[14] J. Bergstra, and Y. Bengio,“Algorithms for hyper-parameter optimization,” in: Advances in neural information processing systems, 2011, pp. 2546–2554.
[15] J. Bergstra, and Y. Bengio, “Random search for hyper-parameter optimization,” J.Mach. Learn. Res. 13 (Feb) (2012) 281–305.
[16] N. M. Aszemi, and P. D. D. Dominic. “Hyperparameter optimization in convolutional neural network using genetic algorithms,” InternationalJournal of Advanced Computer Science and Applications 10.6 (2019).
[17] P. R. Lorenzo, J. Nalepa, M. Kawulok, and L.S. Ramos, “Particle swarm optimization for hyper-parameter selection in deep neural networks,” Proceedings of the genetic and evolutionary computation conference. 2017.
[18] D. E. Kim, and M. Gofman. “Comparison of shallow and deep neural networks for network intrusion detection,” 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (CCWC). IEEE, 2018.
[19] P. Ranjit, and S. Borah, “A detailed analysis of CICIDS2017 dataset for designing Intrusion Detection Systems,” International Journal of Engineering & Technology 7.3.24 (2018): 479-482.
[20] L. Dhanabal, and S. P. Shantharajah, “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 (2015): 446-452.
[21] J. Jinsi, and D. V. Jose, “Deep learning algorithms for intrusion detection systems in internet of things using CIC-IDS 2017 dataset,” International Journal of Electrical and Computer Engineering (IJECE) 13.1 (2023): 1134-1141.
[22] J. Lee, and K. Park, “AE-CGAN model based high performance network intrusion detection system,” Appl. Sci. 2019, 9, 4221.
[23] W, Elmasry, A. Akbulut, and AH. Zaim, “Deep learning approaches for predictive masquerade detection,” Security and Communication Networks 2018.
[24] Mhawi, N. Doaa, A. Aldallal, and S.Hassan. "Advanced feature-selection-based hybrid ensemble learning algorithms for network intrusion detection systems." Symmetry 14.7 (2022): 1461.