On Development of a Machine Learning Based Cloud Security Model for Securing Data from Cyberattacks
Keywords:
Intrusion detection systems, cloud computing, machine learning, feature extractionAbstract
Malicious hackers, cybercriminals, and terrorists are becoming more dangerous because of the proliferation of decentralised computer systems that interact extensively. There must be a specific security solution in place to protect cloud computing because of its extensive use and scattered and decentralised nature. Filters, which keep track of everything from internet traffic to logs to use statistics, can tell the difference between anticipated and unexpected activity on a network by keeping tabs on anything from settings to logs to log files. There have been a lot of research on the location of network security measures in cloud computing environments, as well as the techniques used to implement them. Studies like this aim to find as many intrusions as possible and to speed up and increase the accuracy of detection while reducing false alarms. There is a lot of computation required, but the results aren't as accurate as they could be. Machine learning techniques, both supervised and unsupervised, can be used to detect and prevent attacks in cloud computing environments. For cloud computing, attack detection, network security accuracy, reliability and accessibility are significantly improved by using the recommended technique, which considerably reduces false alarms.
Downloads
References
Ahmim, L. Maglaras, M.A. Ferrag, M. Derdour, H. Janicke, in: A novel hierarchical intrusion detectionsystem based on decision tree and rules-based models, Santorini Island, Greece, 2019, pp. 228–233.
Goeschel, Reducing false positives in intrusion detection systems using data-mining techniques utilizing support vector machines, decision trees, and naive Bayes for off-line analysis, in: In Proceedings of the SoutheastCon 2016, 2016, pp. 1–6.
Hu, T. Li, N. Xie, J. Hu, False positive elimination in intrusion detection based on clustering. In, in: Proceedings of the 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), 2015, pp. 519–523.
Kuttranont, K. Boonprakob, C. Phaudphut, S. Permpol, P. Aimtongkhamand, U. KoKaew, B. Waikham, C. So-In, Parallel KNN and Neighborhood Classification Implementations on GPU for Network IntrusionDetection, J. Telecommun. Electron. Comput. Eng. (JTEC) 9 (2017) 29–33.
Ma, F. Wang, J. Cheng, Y. Yu, Chen, X (2016) A hybrid spectral clustering and deep neural network ensemblealgorithm for intrusion detection in sensor networks, Sensors 16 (2016) 1701.
Mayhew, M. Atighetchi, A. Adler, R. Greenstadt, Use of machine learning in big data analyticsfor insider threat detection, in: In Proceedings of the MILCOM 2015–2015 IEEE Military CommunicationsConference, 2015, pp. 915–922.
Min, J. Long, Q. Liu, J. Cui, W. Chen, TR-IDS: Anomaly-based intrusion detection throughtext-convolutional neural network and random forest, Secur. Commun, Netw, 2018, p. 4943509.
Peng, K.; Leung, V.C.; Huang, Q(2018). Clustering approach based on mini batch kmeans for intrusion detectionsystem over big data. IEEE Access 2018, 6, 11897–11906.
Rigaki, M.; Garcia, S.(2018) Bringing a gan to a knife-fight: Adapting malware communication to avoid detection.In Proceedings of the 2018 IEEE Security and PrivacyWorkshops (SPW), San Francisco, CA, USA, pp. 70–75.
[Teng, N. Wu, H. Zhu, L. Teng, W. Zhang, SVM-DT-based adaptive and collaborative intrusion detection.IEEE/CAA, J. Autom. Sin. 5 (2017) 108–118.
Yu, J. Long, Z. Cai, (2017) Network intrusion detection through stacking dilated convolutional autoencoders, Secur. Commun. Netw. 2017 (2017) 4184196.
Zeng, H. Gu, W. Wei, Guo Y. Deep, Full Range: A Deep Learning Based Network Encrypted TrafficClassification and Intrusion Detection Framework, IEEE Access 7 (2019) 45182–45190.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 A.Daniel (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
