The security feature of SSH protocol ensures the privacy and security of communication content or communication behavior. Often, APTs and malware also use SSH or a variant encryption protocol disguised as SSH to invade a computer or server. In order to solve the shortcomings of existing SSH application classification research, this paper discusses the SSH protocol framework, SSH tunnel and C4.5 decision tree classification algorithm, and briefly discusses the data collection and system development tools of SSH application classification system in this paper. Moreover, the SSH classification model based on machine learning is designed and discussed. Finally, the proposed C4.5 decision tree classification algorithm is tested on the classification results of protocol application. Experimental data show that the average recall and accuracy of C4.5 decision tree classification algorithm for the five protocols are more than 93.17%. Therefore, the C4.5 decision tree classification algorithm proposed in this paper has certain advantages for SSH application classification.

Jing Liu. SSH Application Classification Based on Machine Learning. Machine Learning Theory and Practice (2021), Vol. 2, Issue 3: 20-27. https://doi.org/10.38007/ML.2021.020303.

[1] Acharya, Vishwanath, Bora, et al. Classification of SDSS photometric data using machine learning on a cloud. Current Science: A Fortnightly Journal of Research, 2018, 115(2):249-257. https://doi.org/10.18520/cs/v115/i2/249-257

[2] Donya, Dezfooli, Seyed-Mohammad, et al. Classification of water quality status based on minimum quality parameters: application of machine learning techniques. Modeling Earth Systems and Environment, 2018, 4(1):311-324. https://doi.org/10.1007/s40808-017-0406-9

[3] Saab, Fadi, Jaff, et al. Chronic Total Occlusion Crossing Approach Based on Plaque Cap Morphology: The CTOP Classification. Journal of endovascular therapy: an official journal of the International Society of Endovascular Specialists, 2018, 25(3):284-291. https://doi.org/10.1177/1526602818759333

[4] Bae S Y , Shin J S , Kim Y S , et al. Decision tree analysis on the performance of zeolite-based SCR catalysts. IFAC-PapersOnLine, 2021, 54(3):55-60. https://doi.org/10.1016/j.ifacol.2021.08.218

[5] Baranauskas, Jose, Augusto, et al. A tree-based algorithm for attribute selection. Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies, 2018, 48(4):821-833. https://doi.org/10.1007/s10489-017-1008-y

[6] Kantavat P , Kijsirikul B , Songsiri P , et al. Efficient decision trees for multi-class support vector machines using entropy and generalization error estimation. International Journal of Applied Mathematics & Computer Science, 2018, 28(4):705-717. https://doi.org/10.2478/amcs-2018-0054

[7] Acharya, Vishwanath, Bora, et al. Classification of SDSS photometric data using machine learning on a cloud. Current Science: A Fortnightly Journal of Research, 2018, 115(2):249-257. https://doi.org/10.18520/cs/v115/i2/249-257

[8] Al B , Spm B , Fhc D , et al. Predicting the surfactant-polymer flooding performance in chemical enhanced oil recovery: Cascade neural network and gradient boosting decision tree. Alexandria Engineering Journal, 2021, 61(10):7715-7731. 

[9] Laiou A , Malliou C M , Lenas S A , et al. Autonomous Fault Detection and Diagnosis in Wireless Sensor Networks Using Decision Trees. Journal of Communications, 2019, 14(7):544-552. https://doi.org/10.12720/jcm.14.7.544-552

[10] Rozzini R . Patients' preferences and "paternalistic approach" in elderly patients with atrial fibrillation. BMJ, 2021(7246):1380-1384.

[11] Alavian S M , Sharafi H , Borba H H , et al. Economic evaluation of pan-genotypic generic direct-acting antiviral regimens for treatment of chronic hepatitis C in Iran: a cost-effectiveness study. BMJ Open, 2021, 12(6):161-176. 

[12] Sd A , It B . Interpretable machine learning approach in estimating traffic volume on low-volume roadways - ScienceDirect. International Journal of Transportation Science and Technology, 2020, 9(1):76-88. https://doi.org/10.1016/j.ijtst.2019.09.004

[13] Shetty C , Sowmya B J , Seema S , et al. Air pollution control model using machine learning and IoT techniques - ScienceDirect. Advances in Computers, 2020, 117(1):187-218. https://doi.org/10.1016/bs.adcom.2019.10.006

[14] Sombolestan S M , Rasooli A , Khodaygan S . Optimal path-planning for mobile robots to find a hidden target in an unknown environment based on machine learning. Journal of ambient intelligence and humanized computing, 2019, 10(5):1841-1850. https://doi.org/10.1007/s12652-018-0777-4

[15] Chittora D . How al and machine learning helps in up shilling to better career opportunities. Pc Quest, 2019, 32(3):20-21.

[16] Baumhauer, Judith, Mitten, et al. Using PROs and machine learning to identify "at risk" patients for musculoskeletal injury. Quality of life research: An international journal of quality of life aspects of treatment, care and rehabilitation, 2018, 27(Suppl.1):S9-S9.

[17] Paiva F D , Cardoso R N , Hanaoka G P , et al. Decision-making for financial trading: A fusion approach of machine learning and portfolio selection. Expert Systems with Application, 2019, 115(JAN.):635-655. https://doi.org/10.1016/j.eswa.2018.08.003

[18] Arslan, Atakan, Kardas, et al. Are RNGs Achilles' Heel of RFID Security and Privacy Protocols? Wireless personal communications: An Internaional Journal, 2018, 100(4):1355-1375. https://doi.org/10.1007/s11277-018-5643-3