Abstract

An efficient intrusion detection system is required since more and more networks are connecting to the internet, which has increased the amount of cyberattacks. For an additional layer of security in a cloud environment, intrusion detection techniques must be used in addition to preventive defense methods like firewalls. There are numerous intrusion detection methods and deciding one to use for implementation could be difficult because they all have different features yet share some capabilities in terms of efficiency and accuracy of detection. It is crucial to evaluate how these methods perform. The performance of five data mining algorithms for intrusion detection in a cloud environment was analyzed in this work, and the technique was implemented with excellent results. The Intrusion detection techniques examined in this work are Naive Bayesian (NB), Decision Tree, Support Vector Machine (SVM), K-Nearest Neighbor Classifier (KNN), and Random Forest. The Naïve Bayesian, Decision Tree, Support Vector Machine, K-Nearest Neighbor were trained on NSL-KDD dataset contained 148,517 records in total, of which 80% were used for training and 20% for testing. The analyses were carried out using python's scikit-learn, a powerful library for machine learning that offers a variety of effective tools for machine learning, Jupiter Notebook, a platform for sharing computational documents, Python V-3 Environment, and Anaconda Navigator, a graphical user interface (GUI) that makes it simple to launch programs and manage packages without having to use command-line commands. With an accuracy of 99.68 percent, Random Forest outperformed other algorithms, while Decision Tree, K-Nearest Neighbor, Naive Bayes, and Support Vector Machine had accuracy values of 99.47 percent, 99.17 percent, 90.67 percent, and 96.43 percent, respectively. The Python user interface (UI) module for the model was implemented as an Application Programming Interface (API) utilizing Sklearn modules and PyQt5. On a network server, the Intrusion Detection System under test distinguished between normal and abnormal network traffic. According to the type of attack, abnormal traffic is further categorized. The system will be monitored by this intrusion detection system, which can identify normal and abnormal activities. The best technique that performed better than the others were used to develop a predictive model using Python to implement Random Forest (i.e. a classifier) in a cloud environment, which helped to identify possible attacks on the network. This work presented an intrusion detection system utilizing five data mining techniques.

References

• Muhammad Salman Taj, Syed Irfan Ullah, Abdus Salam & Wajid Ullah Khan. (2020). Enhancing Anomaly based intrusion detection techniques for virtualization in cloud computing using machine learning. (IJCSIS), Vol. 18. No 5.
• Ogunde A.O and Ajibade D.A. (2014). A data Mining System for predicting university students Graduation Grades Using ID3 Decision Tree Algorithm. American Research Institute for policy development, 01 - 26.
• Diptee Agrawal and Chetan Agrawal. (2020). A review of various method of intrusion detection system. Computer Engineering & Intelligent System, Vol.11 No 1, 2020.7.
• Zhao, L., Chaowei, Y., Qun ying, H., Fei, H. (2011) Big Data and cloud computing: innovation opportunities and challenges. International Journal of Digital Earth. DOI: 10.1080/17538947.2016.1239771. Vol 10, 2017 Issue 1, pages 13 -53. Informa UK Limited.
• Zhang, A. (2011). Survey of Data Mining Usage in Cloud Computing. EEE International Conference on Data Mining, Vol. III, no. 3/2011, pages 472 – 481.
• Briscoe, G and Marinos, A. (2009). Digital ecosystems in the clouds: Towards community cloud computing. Digital Ecosystems and Technologies, 2009. DEST '09. 3rd IEEE International Conference on. DOI: 10.1109/DEST.2009.5276725.Brown, L. D., Hua, H., and Gao, C. 2003. A widget framework for augmented interaction in SCAPE.
• Rosado, D. G., Rafael, G., Daniel, M. and Eduardo, F. (2011). security Analysis in the Migration to Cloud Environments. Future Internet, 4, pg.469-487; doi:10.3390/fi4020469.
• Mather, T., Kumaraswamy, S. and Latif, S. (2009). Cloud Security and Privacy: An Enterprise Perspective on Risks and Compliance. O’Reilly Media, Inc. Journal of Information Security, Vol.6 No.2. pages 777 -780.
• Li and Ping (2009). A Survey on Open-source Cloud Computing Solutions. VIII Workshop Clouds, Grids e Applicators. Caixa Postal 7851 – 50732-970 – Recife – PE
• Gupta, A., Suri, B., Kumar, V., & Jain, P. (2020). Extracting rules for vulnerabilities detection with static metrics using machine learning. International Journal of System Assurance Engineering and Management, 1-12. Vol. 9, DOI:10.1007/s13198-020-01036-0.
• Gupta D, Singhal S, Malik S & Singh A. (2016). Network intrusion detection system using various data mining techniques. In Research Advances in Integrated Navigation System (RAINS). IEEE Catalog Number: CFP16RAI-POD.page Nos 252 - 257, Vol.7, Issue 5.
• Adetunmibi A.O. et al., (2008). Network intrusion Detection Based on Rough Set and K-Nearest Neighbor. International Journal of Computing and ICT Research, Vol. 2, No 1 pp. 60 -66. http.www.ijcir.org/volume1-number 2/article7.pdf.
• Ahmadzadegan, M.H., Khorshidvand, A. A., & Valian M.G. (2015). Low-rate false alarm intrusion detection with generic Algorithm Approach. INSPEC Accession Number: 15870906.IEEE, 2ND International Conference on Knowledge - Based Engineering and Innovation (KBEI). USA, pages 1045 -1048. IEEE. https://doi.org/10.1109/KBEI.2015.7436188
• Sour Leang .C (2017). Understanding about Cloud Computing.https://medium.com/@sourleangchhean/understanding-about-cloud-computing 76545af3b06a
• Cloud Security Alliance Innovation Conference (2012). https://cloudsecurityalliance.org/events/csa-innovation-conference-2012/
• Rittenhouse, J. (2010). Cloud Computing Implementation, Management, and Security. CRC Press Taylor & Francis Group. International Standard Book Number: 978-1-43980680-7 (Hardback). CRC Press. Vol 2, Issue 1.
• Saouabi, M., and Abdellah, E. (2020). A data mining process using classification techniques for employability prediction. IJEECS visitor statistics. DOI: http://doi.org/10.11591/ijeecs.v14.i2.pp1025-1029
• Neelamegam, S. and Ramaraj, E. (2013). Classification algorithm in Data mining: An Overview. International Journal of P2P Network Trends and Technology. Vol.3 Issue 5.
• Adebayo, A., Shi, Z., Shi, Z., Olumide S., A. (2006) in IFIP International Federation for Information Processing, Volume 228, Intelligent Information Processing III, eds. Z. Shi, Shimohara K., Feng D., (Boston; Springer), pp. 525-530.
• Ray, P (2018). A survey on Internet of Things architectures J. King Saud Univ. – Computer. Inf. Sci., 30 (3), pp. 291-31