臺灣博碩士論文加值系統

窄帶物聯網(Narrow Band Internet of Things, NB-IoT)是一種低功耗廣域網路(Low Power Wide Area Network, LPWAN)技術，並已在第三代合作夥伴計畫(3rd Generation Partnership Project, 3GPP)的標準第13版中被納入，也證明了NB-IoT在物聯網的應用上有著巨大的潛力，因此物聯網裝置數量將會爆炸性的成長，也讓物聯網的網路環境成為殭屍網路(Botnet)的溫床，各個物聯網裝置與平臺將遭受阻斷服務攻擊(Denial-of-service, DoS )的威脅，然而NB-IoT具有較低速率的特性(上行鏈路為60kpps)所以並不是實施高流量DoS攻擊的理想環境，則低速阻斷服務攻擊(Low-Rate Denial-of-Service, LDoS)才是NB-IoT環境中的主要攻擊手段，在此環境中，攻擊者可以將攻擊封包隱藏在足夠低速率的資料流程當中以逃避檢測使得檢測的困難度被大幅提高，目前已經有許多採用人工智慧的卷積神經網路(Convolutional Neural Network, CNN)來識別該攻擊的特徵，然而這種傳統的方法會因為資料量不夠多元導致擬合過度(Overfitting)的現象，為了改善此問題，本文使用模擬退火演算法(Simulated Annealing, SA)來進行卷積神經網路的權重調整已達到更好的全域搜索，實驗結果表明，本文所提之方法可以更有效地檢測出LDoS攻擊。

Narrow Band Internet of Things is a Low Power Wide Area Network technology and has been included in the 13th edition of the 3rd Generation Partnership Project standard. It also proves that NB-IoT has great potential in the application of the Internet of Things. Therefore, the Internet of Things The number of devices will grow explosively, and the Internet of Things network environment will become a hotbed of Botnets. Various Internet of Things devices and platforms will be threatened by Denial-of-service. However, NB-IoT has the characteristics of lower speed (uplink Road is 60kpps) so it is not an ideal environment for high-traffic DoS attacks. Low-Rate Denial-of-Service is the main attack method in the NB-IoT environment. In this environment, the attacker can hide the attack packet in Avoiding detection in a data stream with a sufficiently low rate has greatly increased the difficulty of detection. There are already many Convolutional Neural Networks that use artificial intelligence to identify the characteristics of the attack. However, this traditional method will cause the amount of data to be insufficiently diverse. In order to improve the phenomenon of overfitting, this article uses Simulated Annealing to adjust the weight of the convolutional neural network to achieve better global search. The experimental results show that the method proposed in this article can detect LDoS attacks more effectively.

摘要 I
ABSTRACT II
致謝 III
目錄 IV
圖目錄 VI
表目錄 VII
第1章 緒論 1
1.1 前言 1
1.2 研究動機與目的 2
1.3 論文結構 3
第2章 背景介紹及相關文獻 4
2.1 入侵偵測系統 4
2.1.1 目前侵偵測系統的研究方法 4
2.2 窄帶物聯網 5
2.3 低速阻斷服務攻擊 6
2.4 類神經網路 7
2.4.1 卷積神經網路 9
2.5 模擬退火演算法 11
2.6 優化神經網路的相關論文 12
第3章 問題定義及架構 15
3.1 問題定義 15
3.2 流程架構圖 16
3.3 資料集 17
3.3.1 攻擊流量壓在60kbps 19
3.3.2 特徵標準化 20
3.3.3 獨熱編碼 21
3.4 建立模型 22
3.5 超參數調整 23
3.6 結合模擬退火算法的卷積神經網路 24
3.6.1 模擬退火法調整流程 26
第4章 實驗結果與分析 31
4.1 實驗環境 31
4.2 模型超參數調整 31
4.2.1 批量大小 32
4.2.2 Epoch 33
4.3 實驗結果 34
4.3.1 混淆矩陣 37
第5章 結論與未來展望 38
參考文獻 39

[1] D. Wang, D. Chen, B. Song, N. Guizani, X. Yu and X. Du, "From IoT to 5G I-IoT: The next generation IoT-based intelligent algorithms and 5G technologies," IEEE Communications Standards Magazine, vol. 56, no. 10, pp. 114-120, October 2018.
[2] C. F. Lai, M. Y. Chen, J. W. Lin, "Guest Editorial: Edge Computing – The New Frontier of IoT and 5G Applications," Journal of Internet Technology, vol. 21, no. 1, pp. 261-262, 2020.
[3] V. Sharma, J. Kim, Y. Ko,I. You, J. T. Seo, "An Optimal Security Management Framework for Backhaul-aware 5G-Vehicle to Everything (V2X)," Journal of Internet Technology, vol. 21, no. 1, pp. 245-260, 2020.
[4] S. Kitanov, T. Janevski, "Fog Computing Service Orchestration Mechanisms for 5G Networks," Journal of Internet Technology, vol. 19, no. 1, pp. 297-305, 2018.
[5] H. Magsi, A. H. Sodhro, F. A. Chachar and S. A. Abro, "Evolution of 5G in Internet of medical things," in International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), March 2018.
[6] K. L. Lueth, "State of the IoT 2018: Number of IoT devices now at 7B–Market accelerating," 2018. [Online]. Available: https://iot-analytics.com/state-of-the-iot-update-q1-q2-2018-number-of-iot-devices-now-7b/.
[7] Babla, C., "Cellular IoT and LPWAN - addressing the industry FUD," 2017. [Online]. Available: https://community.arm.com/iot/b/internet-of-things/posts/cellular-iot-and-lpwan-_2d00_-addressing-the-industry-fud.
[8] L.Ratliff, S.Lucero, "ARM elbows its way into an already crowded NB-IoT semiconductor market," 2017. [Online]. Available: https://technology.ihs.com/589151/arm-elbows-its-way-into-an-already-crowded-nb-iot-semiconductor-market.
[9] J. Wurm, K. Hoang, O. Arias, A.-R. Sadeghi and Y. Jin, "Security analysis on consumer and industrial IoT devices," in 21st Asia and South Pacific Design Automation Conference, pp. 519-524, 2016.
[10] S.Y. Moon, J. H. Park, J. H. Park, "Authentications for Internet of Things Security: Threats, Challenges and Studies," Journal of Internet Technology, vol. 19, no. 2, pp. 349-358, 2018.
[11] T. H. Lin, C. C. Lee, C. H. Chang, "WSN Integrated Authentication Schemes Based on Internet of Things," Journal of Internet Technology, vol. 19, no. 4, pp. 1043-1053, 2018.
[12] Y. S. Zhao, H. C. Chao, "A Green and Secure IoT Framework for Intelligent Buildings based on Fog Computing," Journal of Internet Technology, vol. 19, no. 3, pp. 837-843, 2018.
[13] P. Salva-Garcia, J. M. Alcaraz-Calero, Q. Wang, J. B. Bernabe and A. Skarmeta, "5G NB-IoT: Efficient network traffic filtering for multitenant IoT cellular networks," Security and Communication Networks, vol. 2018, pp. 1-21, December 2018.
[14] J. Brynielsson and R. Sharma, “Detectability of Low-Rate HTTP Server DoS Attacks using Spectral Analysis,” in IEEE Conference on Advances in Social Networks Analysis and Mining, pp. 954-961, August 2015.
[15] Y. Fu, F. Lou, F. Meng, Z. Tian, H. Zhang and F. Jiang, “An intelligent network attack detection method based on RNN,” in IEEE International Conference on Data Science in Cyberspace, pp. 486-489, January 2018.
[16] C. Yin, Y. Zhu, J. Fei and X. He, "A deep learning approach for intrusion detection using recurrent neural networks," IEEE Access, vol. 5, pp. 21954-21961, 2017.
[17] W.-H. Lin, H. Lin, P. Wang, B. Wu and J. Tsai, “Using Convolutional Neural Networks to Network Intrusion Detection for Cyber Threats,” IEEE International Conference on Applied System Invention, pp. 1107-1110, 2018.
[18] R. Vinayakumar, K. Soman and P. Poornachandran, “Applying convolutional neural network for network intrusion detection,” International Conference on Advances in Computing Communications and Informatics, pp. 1222-1228, 2017.
[19] A. Ratilainen, "NB-IoT Presentation for IETF LPWAN," 2016. [Online]. Available: https://datatracker.ietf.org/meeting/97/materials/slides-97-lpwan-30-nb-iot-presentation-00.
[20] E. Adi, Z. Baig, C. P. Lam and P. Hingston, “Low-rate Denial-of-service attacks against HTTP/2 services,” International Conference on IT Convergence and Security, pp. 133-139, August 2015.
[21] P. B. a. G. T. B. A. Pratomo, “Unsupervised approach for detecting low rate attacks on network traffic with autoencoder,” in 2018 International Conference on Cyber Security and Protection of Digital Services Cyber Security, pp. 1-8, June 2018.
[22] Z. J. Wu, L. Y. Zhang and M. Yue, "Low-rate DoS attacks detection based on network multifractal," IEEE Trans. Depend. Secure Comput, vol. 13, no. 5, pp. 559-567, October 2016.
[23] A. Yulianto, P. Sukarno and N.A Suwastika, "Improving adaboost-based intrusion detection system (IDS) performance on CIC IDS 2017 dataset," Journal of Physics: Conference Series, vol. 1192, no. 1, pp. 12-18, June 2019.
[24] Y. Li and L. Guo, "An active learning based TCM-KNN algorithm for supervised network intrusion detection," Comput. Secur, vol. 26, no. 7, pp. 459-467, 2007.
[25] C. Tang, Y. Xiang, Y. Wang, J. Qian and B. Qiang, "Detection and classification of anomaly intrusion using hierarchy clustering and SVM," Security and Communication Networks, vol. 9, no. 16, pp. 3401-3411.
[26] C.F. Tsai and C.Y. Lin, "A Triangle Area Based Nearest Neighbors Approach to Intrusion Detection," Pattern Recognition, vol. 43, no. 1, pp. 222-229, 2010.
[27] G. Stein, B. Chen, A.S. Wu and K.A. Hua, “Decision Tree Classifier for Network Intrusion Detection with GA-Based Feature Selection,” in 43rd ACM Southeast Conference, 2005.
[28] R. C. Staudemeyer, "Applying long short-term memory recurrent neural networks to intrusion detection," South African Computer Journal, vol. 56, no. 1, pp. 136-154, 2015.
[29] R. Upadhyay and D. Pantiukhin, “Application of convolutional neural network to intrusion type recognition,” Ben-Gurion University of the Negev Tech, 2017.
[30] L. Zhang, H. Pan, B. Wang, L. Zhang, Z. Fu, "Interval Fuzzy C-means Approach for Incomplete Data Clustering Based on Neural Networks," Journal of Internet Technology, vol. 19, no. 4, pp. 1089-1098, 2018.
[31] K. Srinivasan, A. K. Cherukuri, D. R. Vincent, A. Garg, B. Y. Chen, "An Efficient Implementation of Artificial Neural Networks with K-fold Cross-validation for Process Optimization," Journal of Internet Technology, vol. 20, no. 4, pp. 1213-1225, 2019.
[32] L. Liu, P. Wu, X. Wang, "Short-time Traffic Flow Prediction Based on Wavelet Neural Network," Journal of Internet Technology, vol. 20, no. 4, pp. 1237-1246, 2019.
[33] R. R. Chakravarthi, E. Chandra, "Kernel Based Artificial Neural Network Technique to Enhance the Performance and Accuracy of On-Line Signature Recognition," Journal of Internet Technology, vol. 21, no. 2, pp. 447-455, 2020.
[34] D. H. Hubel and T. N. Wiesel, "Receptive fields binocular interaction and functional architecture in the cat's visual cortex," The Journal of Physiology, vol. 160, pp. 106-154, 1962.
[35] B. Yao, H. Zhou, J. Yin, G. Li, C. Lv, "Small Sample Image Recognition Based on CNN and RBFNN," Journal of Internet Technology, vol. 21, no. 3, pp. 881-889, 2020.
[36] Y. Li, K. Liu, W. Zhao, Y. Huang, "Target Detection Method for SAR Images Based on Feature Fusion Convolutional Neural Network," Journal of Internet Technology, vol. 21, no. 3, pp. 863-870, 2020.
[37] Y. Su, C. Chen, T. Chen, C. Cheng, "Chinese Microblog Sentiment Analysis by Adding Emoticons to Attention-Based CNN," Journal of Internet Technology, vol. 21, no. 3, pp. 821-829, 2020.
[38] S. P. K. Arachchi, T. K. Shih, C. Lin, G. Wijayarathna, "Deep Learning-Based Firework Video Pattern Classification," Journal of Internet Technology, vol. 20, no. 7, pp. 2033-2042, 2019.
[39] J. Y. Li, J. H. Li, "Prompt Image Search with Deep Convolutional Neural Network via Efficient Hashing Code and Addictive Latent Semantic Layer," Journal of Internet Technology, vol. 19, no. 3, pp. 949-957, 2018.
[40] N. Metropolis, A. W. Rosenbluth, M. N. Rosenbluth, A. H. Teller and E. Teller, "Equation of state calculations by fast computing machines," Journal of Chemical Physics, vol. 21, no. 6, pp. 1087-1092, June 1953.
[41] S. Kirkpatrick, C. D. Gelatt and M. P. Vecchi, "Optimization by simulated annealing," Science, vol. 220, no. 4598, pp. 671-680, 1983.
[42] C. Wen. Chiang, "Two Novel Genetic Operators for Task Matching and Scheduling in Heterogeneous Computing Environments," Journal of Internet Technology, vol. 13, no. 5, pp. 773-784, 2012.
[43] J. Niu, H. Zhao, W. Zhu, "Feature Selection with Test Cost Constraint through a Simulated Annealing Algorithm," Journal of Internet Technology, vol. 17, no. 6, pp. 1133-1140, 2016.
[44] A. A. Nasr, N. A. Bahnasawy, G. Attiya, A. E. Sayed, "Cloudlet Scheduling Based Load Balancing on Virtual Machines in Cloud Computing Environment," Journal of Internet Technology, vol. 20, no. 5, pp. 1371-1378, 2019.
[45] C. L. Chang, C. J. Chen, H. T. Lee, C. Y. Chang, S. T. Chen, "Bounding the Sensing Data Collection Time with Ring-based Routing for Industrial Wireless Sensor Networks," Journal of Internet Technology, vol. 21, no. 3, pp. 673-680, 2020.
[46] L. Xie and A. L. Yuille, "Genetic CNN," in IEEE International Conference on Computer Vision, pp.1388-1397, 2017.
[47] E. Real, S. Moore, A. Selle, S. Saxena, Y. L. Suematsu, Q. Le, "Large-scale evolution of image classifiers," in International Conference on Machine Learning, pp. 2902-2911, 2017.
[48] C.-W. Tsai, C.-H. Hsia, S.-J. Yang, S.-J. Liu and Z.-Y. Fang, "Optimizing hyperparameters of deep learning in predicting bus passengers based on simulated annealing," Applied Soft Computing, vol. 88, March 2020.
[49] E. P. L. Shiang, W. C. Chien, C. F. Lai, and H. C. Chao, "Gated Recurrent Unit Network-based Cellular Trafile Prediction," in International Conference on Information Networking (ICOIN), pp. 471-476, March 2020.
[50] V. Ayumi, L. M. R. Rere, M. I. Fanany and A. M. Arymurthy, "Optimization of convolutional neural network using microcanonical annealing algorithm," in International Conference on Advanced Computer Science and Information Systems, pp. 506-511, October 2016.
[51] L. M. R. Rere, M. I. Fanany and A. M. Arymurthy, "Metaheuristic algorithms for convolution neural network," Computational Intelligence and Neuroscience, vol. 2016, 2016.
[52] Z. Li, Z. Qin, K. Huang, X. Yang and S. Ye, “Intrusion detection using convolutional neural networks for representation learning,” in International Conference on Neural Information Processing, pp. 858-866, 2017.
[53] C. Hohn and C. R. Reeves, “The crossover landscape for the onemax problem,” in 2nd Nord. Workshop Genet. Algorithms, pp. 27-43, 1996.