Retracted: DETECTING ATTACKS ON MQTT-IOT PROTOCOL USING ML TECHNIQUES
DOI:
https://doi.org/10.4314/jfas.v12i2.17Keywords:
Security; Internet of Things (IoT); MQTT; Intrusion Detection System (IDS); ML Techniques.Abstract
IoT devices are less capable of handling security, because their computational power is low and applying a complex security algorithm will drain them very easily. To improve this situation, we have applied various algorithms at the gateway, to detect the intrusion. In this sense, the purpose of this work is to improve intrusion detection systems for low powered IoT devices that use lightweight MQTT protocols. The omnipresent IoT devices rely on encryption-based security measures due to speed and lightweight constraints. It uses ensemble methods which have proved to be optimal in the above work. Ensemble methods achieved a log_loss of 0.44 and an accuracy of 98.72% for multiclass classification. The work also uses Convolutional Neural Networks after converting tabular data to set of images which achieved a log_loss of 0.019 and accuracy of 99.3%. It further aims to implement these in IDS.
Downloads
Download data is not yet available.
References
[1] TAVALLAEE, Mahbod, BAGHERI, Ebrahim, LU, Wei, and al. A detailed analysis of the KDD CUP 99 data set. In: 2009 IEEE symposium on computational intelligence for security and defense applications. IEEE, 2009, p. 1-6, doi: 10.1109/CISDA.2009.5356528
[2] CHAKRABARTY, Biswapriyo, CHANDA, Omit, and ISLAM, Md Saiful. Anomaly based intrusion detection system using genetic algorithm and K-centroid clustering. International Journal of Computer Applications, 2017, vol. 163, no 11, p. 13-17, doi: 10.5120/ijca2017913762.
[3] HASAN, Md Al Mehedi, NASSER, Mohammed, PAL, Biprodip, and al. Support vector machine and random forest modeling for intrusion detection system (IDS). Journal of Intelligent Learning Systems and Applications, 2014, vol. 2014, doi: 10.4236/jilsa.2014.61005.
[4] NIETO, PJ García, FERNÁNDEZ, JR Alonso, LASHERAS, F. Sánchez, and al. A new improved study of cyanotoxins presence from experimental cyanobacteria concentrations in the Trasona reservoir (Northern Spain) using the MARS technique. Science of the total environment, 2012, vol. 430, p. 88-92, doi: 10.1016/j.scitotenv.2012.04.068.
[5] SEO, Jae-Hyun and KIM, Yong-Hyuk. Machine-learning approach to optimize smote ratio in class imbalance dataset for intrusion detection. Computational Intelligence and Neuroscience, 2018, vol. 2018, doi: 10.1155/2018/9704672.
[6] ASHFAQ, Rana Aamir Raza, WANG, Xi-Zhao, HUANG, Joshua Zhexue, and al. Fuzziness based semi-supervised learning approach for intrusion detection system. Information Sciences, 2017, vol. 378, p. 484-497, doi: 10.1016/j.ins.2016.04.019.
[7] SINGH, Raman, KUMAR, Harish, and SINGLA, R. K.An intrusion detection system using network traffic profiling and online sequential extreme learning machine. Expert Systems with Applications, 2015, vol. 42, no 22, p. 8609-8624, doi: 10.1016/j.eswa.2015.07.015.
[8] KWON, Donghwoon, KIM, Hyunjoo, KIM, Jinoh, and al. A survey of deep learning-based network anomaly detection. Cluster Computing, 2017, p. 1-13, doi: 10.1007/s10586-017-1117-8.
[9] NIETO, PJ García, TORRES, J. Martínez, DE COS JUEZ, Francisco Javier, and al. Using multivariate adaptive regression splines and multilayer perceptron networks to evaluate paper manufactured using Eucalyptus globulus. Applied Mathematics and Computation, 2012, vol. 219, no 2, p. 755-763, doi 10.1016/j.amc.2012.07.001
[10] LI, Yuancheng, MA, Rong, and JIAO, Runhai. A hybrid malicious code detection method based on deep learning. International Journal of Security and Its Applications, 2015, vol. 9, no 5, p. 205-216, doi:10.14257/ijsia.2015.9.5.21
11] TAO, Xiaoling, KONG, Deyan, WEI, Yi, and al. A big network traffic data fusion approach based on fisher and deep auto-encoder. Information, 2016, vol. 7, no 2, p. 20, doi: 10.3390/info7020020.
[12] KIM, Jihyun, KIM, Jaehyun, THU, Huong Le Thi, and al. Long short term memory recurrent neural network classifier for intrusion detection. In : 2016 International Conference on Platform Technology and Service (PlatCon). IEEE, 2016. p. 1-5, doi: 10.1109/PlatCon.2016.7456805.
[13] AN, Xingshuo, ZHOU, Xianwei, LÜ, Xing, and al. Sample selected extreme learning machine based intrusion detection in fog computing and MEC. Wireless Communications and Mobile Computing, 2018, vol. 2018, doi : 10.1155/2018/7472095
[14] LU, Fan and WANG, Liejun. Intrusion detection system based on integration of neural network for wireless sensor network. J. Softw. Eng, 2014, vol. 8, p. 225-238, doi: 10.3923/jse.2014.225.238.
[15] ZARPELÃO, Bruno Bogaz, MIANI, Rodrigo Sanches, KAWAKANI, Cláudio Toshio, and al. A survey of intrusion detection in Internet of Things. Journal of Network and Computer Applications, 2017, vol. 84, p. 25-37, doi: 10.1016/j.jnca.2017.02.009.
[16]KOLIAS, Constantinos, KAMBOURAKIS, Georgios, STAVROU, Angelos, and al. Intrusion detection in 802.11 networks: empirical evaluation of threats and a public dataset. IEEE Communications Surveys & Tutorials, 2015, vol. 18, no 1, p. 184-208, doi:10.1109/Comst.2015.2402161.
[17] AMINANTO, Muhamad Erza, TANUWIDJAJA, Harry Chandra, YOO, Paul D., and al. Wi-Fi intrusion detection using weighted-feature selection for neural networks classifier. In : 2017 International Workshop on Big Data and Information Security (IWBIS). IEEE, 2017. p. 99-104, doi: 10.1109/IWBIS.2017.8275109
[18] QIN, Zhi-Quan, MA, Xing-Kong, and WANG, Yong-Jun. Attentional Payload Anomaly Detector for Web Applications. In: International Conference on Neural Information Processing. Springer, Cham, 2018. p. 588-599, doi: 10.1007/978-3-030-04212-7_52.
[19] HALABI, Talal and BELLAICHE, Martine. How to evaluate the defense against dos and ddos attacks in cloud computing: a survey and taxonomy. International Journal of Computer Science and Information Security, 2016, vol. 14, no 12, p. 1.
[20] Joseph R. and Baptiste R., Ensemble methods: bagging, boosting and stacking, Towards DataScience,https://towardsdatascience.com/ensemble-methods-bagging-boosting- and- stacking- c9214a10a205, 2019.
[21] Sumit S., A Comprehensive Guide to Convolutional Neural Networks, the ELI5 way”, Tow. Dat. Sci., https://towardsdatascience.com/a-comprehensive-guide-to-convolutional- neural-networks-the-eli5-way-3bd2b1164a53, 2018.
[2] CHAKRABARTY, Biswapriyo, CHANDA, Omit, and ISLAM, Md Saiful. Anomaly based intrusion detection system using genetic algorithm and K-centroid clustering. International Journal of Computer Applications, 2017, vol. 163, no 11, p. 13-17, doi: 10.5120/ijca2017913762.
[3] HASAN, Md Al Mehedi, NASSER, Mohammed, PAL, Biprodip, and al. Support vector machine and random forest modeling for intrusion detection system (IDS). Journal of Intelligent Learning Systems and Applications, 2014, vol. 2014, doi: 10.4236/jilsa.2014.61005.
[4] NIETO, PJ García, FERNÁNDEZ, JR Alonso, LASHERAS, F. Sánchez, and al. A new improved study of cyanotoxins presence from experimental cyanobacteria concentrations in the Trasona reservoir (Northern Spain) using the MARS technique. Science of the total environment, 2012, vol. 430, p. 88-92, doi: 10.1016/j.scitotenv.2012.04.068.
[5] SEO, Jae-Hyun and KIM, Yong-Hyuk. Machine-learning approach to optimize smote ratio in class imbalance dataset for intrusion detection. Computational Intelligence and Neuroscience, 2018, vol. 2018, doi: 10.1155/2018/9704672.
[6] ASHFAQ, Rana Aamir Raza, WANG, Xi-Zhao, HUANG, Joshua Zhexue, and al. Fuzziness based semi-supervised learning approach for intrusion detection system. Information Sciences, 2017, vol. 378, p. 484-497, doi: 10.1016/j.ins.2016.04.019.
[7] SINGH, Raman, KUMAR, Harish, and SINGLA, R. K.An intrusion detection system using network traffic profiling and online sequential extreme learning machine. Expert Systems with Applications, 2015, vol. 42, no 22, p. 8609-8624, doi: 10.1016/j.eswa.2015.07.015.
[8] KWON, Donghwoon, KIM, Hyunjoo, KIM, Jinoh, and al. A survey of deep learning-based network anomaly detection. Cluster Computing, 2017, p. 1-13, doi: 10.1007/s10586-017-1117-8.
[9] NIETO, PJ García, TORRES, J. Martínez, DE COS JUEZ, Francisco Javier, and al. Using multivariate adaptive regression splines and multilayer perceptron networks to evaluate paper manufactured using Eucalyptus globulus. Applied Mathematics and Computation, 2012, vol. 219, no 2, p. 755-763, doi 10.1016/j.amc.2012.07.001
[10] LI, Yuancheng, MA, Rong, and JIAO, Runhai. A hybrid malicious code detection method based on deep learning. International Journal of Security and Its Applications, 2015, vol. 9, no 5, p. 205-216, doi:10.14257/ijsia.2015.9.5.21
11] TAO, Xiaoling, KONG, Deyan, WEI, Yi, and al. A big network traffic data fusion approach based on fisher and deep auto-encoder. Information, 2016, vol. 7, no 2, p. 20, doi: 10.3390/info7020020.
[12] KIM, Jihyun, KIM, Jaehyun, THU, Huong Le Thi, and al. Long short term memory recurrent neural network classifier for intrusion detection. In : 2016 International Conference on Platform Technology and Service (PlatCon). IEEE, 2016. p. 1-5, doi: 10.1109/PlatCon.2016.7456805.
[13] AN, Xingshuo, ZHOU, Xianwei, LÜ, Xing, and al. Sample selected extreme learning machine based intrusion detection in fog computing and MEC. Wireless Communications and Mobile Computing, 2018, vol. 2018, doi : 10.1155/2018/7472095
[14] LU, Fan and WANG, Liejun. Intrusion detection system based on integration of neural network for wireless sensor network. J. Softw. Eng, 2014, vol. 8, p. 225-238, doi: 10.3923/jse.2014.225.238.
[15] ZARPELÃO, Bruno Bogaz, MIANI, Rodrigo Sanches, KAWAKANI, Cláudio Toshio, and al. A survey of intrusion detection in Internet of Things. Journal of Network and Computer Applications, 2017, vol. 84, p. 25-37, doi: 10.1016/j.jnca.2017.02.009.
[16]KOLIAS, Constantinos, KAMBOURAKIS, Georgios, STAVROU, Angelos, and al. Intrusion detection in 802.11 networks: empirical evaluation of threats and a public dataset. IEEE Communications Surveys & Tutorials, 2015, vol. 18, no 1, p. 184-208, doi:10.1109/Comst.2015.2402161.
[17] AMINANTO, Muhamad Erza, TANUWIDJAJA, Harry Chandra, YOO, Paul D., and al. Wi-Fi intrusion detection using weighted-feature selection for neural networks classifier. In : 2017 International Workshop on Big Data and Information Security (IWBIS). IEEE, 2017. p. 99-104, doi: 10.1109/IWBIS.2017.8275109
[18] QIN, Zhi-Quan, MA, Xing-Kong, and WANG, Yong-Jun. Attentional Payload Anomaly Detector for Web Applications. In: International Conference on Neural Information Processing. Springer, Cham, 2018. p. 588-599, doi: 10.1007/978-3-030-04212-7_52.
[19] HALABI, Talal and BELLAICHE, Martine. How to evaluate the defense against dos and ddos attacks in cloud computing: a survey and taxonomy. International Journal of Computer Science and Information Security, 2016, vol. 14, no 12, p. 1.
[20] Joseph R. and Baptiste R., Ensemble methods: bagging, boosting and stacking, Towards DataScience,https://towardsdatascience.com/ensemble-methods-bagging-boosting- and- stacking- c9214a10a205, 2019.
[21] Sumit S., A Comprehensive Guide to Convolutional Neural Networks, the ELI5 way”, Tow. Dat. Sci., https://towardsdatascience.com/a-comprehensive-guide-to-convolutional- neural-networks-the-eli5-way-3bd2b1164a53, 2018.
Published
2020-04-26
How to Cite
GHRIB, T.; BENMOHAMMED, M.; SHEKHAR PANDEY, P. Retracted: DETECTING ATTACKS ON MQTT-IOT PROTOCOL USING ML TECHNIQUES. Journal of Fundamental and Applied Sciences, [S. l.], v. 12, n. 2, p. 774–799, 2020. DOI: 10.4314/jfas.v12i2.17. Disponível em: https://jfas.info/index.php/JFAS/article/view/788. Acesso em: 30 jan. 2025.
Issue
Section
Articles
Submissions
