基於卷積神經網路的低速阻斷服務攻擊檢測

Low-Rate Denial-of-Service detection based on Convolutional Neural Network

蔡旻諺(Min-Yan Tsai)；徐禾瀚(Augustine Sii Ho Hann)；卓信宏(Hsin-Hung Cho)

低速阻斷服務攻擊 ； 入侵偵測系統 ； 卷積神經網路 ； Low-Rate Denial-of-Service ； Intrusion Detection System ； Convolutional neural networks

資訊安全通訊

26卷3期（2020 / 08 / 01）

51 - 62

繁體中文

低速阻斷服務攻擊（Low-Rate Denial-of-Service, LDoS）是低運算能力的環境中常面臨攻擊手段，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當中以逃避檢測使得檢測的困難度被大幅提高，使得傳統的方法會因為資料量不夠多元導致無法順利提取特徵而無法精準識別攻擊者，為了改善此問題，本文採用人工智慧的卷積神經網路（Convolutional Neural Network, CNN）以達到更好的全域搜索，實驗結果表明，本文所提之方法可以有效地檢測出LDoS攻擊。

Low-Rate Denial-of-Service (LDoS) is an attack method often faced in environments with low computing power. In this environment, attackers can hide attack packets in sufficiently low-rate data streams to escape detection has greatly increased the difficulty of detection, which makes traditional methods unable to extract features smoothly due to insufficient data and cannot accurately identify attackers. In order to improve this problem, this article uses artificial intelligence convolutional neural networks (CNN) to achieve stronger global search, the experimental results show that the method proposed in this article can effectively detect LDoS attacks.

1. Available: https://community.arm.com/iot/b/internet-of-things/posts/cellular-iot-and-lpwan-_2d00_-addressing-the-industry-fud.
2. Babla, C., “Cellular IoT and LPWAN - addressing the industry FUD,” 2017. [Online].
3. Brynielsson, J.,Sharma, R.(2015).Detectability of Low-Rate HTTP Server DoS Attacks using Spectral Analysis.IEEE Conference on Advances in Social Networks Analysis and Mining
4. Chen, A.,Chen, B.,Wu, A.S.,Hua, K.A.(2005).Decision Tree Classifier for Network Intrusion Detection with GA-Based Feature Selection.43rd ACM Southeast Conference
5. Li, Y.,Guo, L.(2007).An active learning based TCM-KNN algorithm for supervised network intrusion detection.Comput. Secur,26(7),459-467.
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. Magsi, H.,Sodhro, A. H.,Chachar, F. A.,Abro, S. A.(2018).Evolution of 5G in Internet of medical things.International Conference on Computing, Mathematics and Engineering Technologies (iCoMET)
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. Salva-Garcia, P.,Alcaraz-Calero, J. M.,Wang, Q.,Bernabe, J. B.,Skarmeta, A.(2018).5G NB-IoT: Efficient network traffic filtering for multitenant IoT cellular networks.Security and Communication Networks,2018,1-21.
10. Tang, C.,Xiang, Y.,Wang, Y.,Qian, J.,Qiang, B..Detection and classification of anomaly intrusion using hierarchy clustering and SVM.Security and Communication Networks,9(16),3401-3411.
11. Tsai, F.,Lin, C.Y.(2010).A Triangle Area Based Nearest Neighbors Approach to Intrusion Detection.Pattern Recognition,43(1),222-229.
12. Wang, D.,Chen, D.,Song, B.,Guizani, N,Yu, X.,Du, X.(2018).From IoT to 5G I-IoT: The next generation IoT-based intelligent algorithms and 5G technologies.IEEE Communications Standards Magazine,56(10),114-120.
13. Wurm, J.,Hoang, K.,Arias, O.,Sadeghi, A.-R.,Jin, Y.(2016).Security analysis on consumer and industrial IoT devices.21st Asia and South Pacific Design Automation Conference

1. 陳仕弘(2023)。資訊安全威脅與治理政策之探討。管理資訊計算，12(特刊1)，1-12。
2. (2024)。基於卷積神經網路之校園緊急求助系統。慈濟科技大學學報，13，125-142。