Identifying Cyberattacks in Cloud ‎Computing Service Frameworks Through ‎Correlation-Driven Feature

  • Authors

    • smitha GV Assistant Professor, ‎Research Scholar, Department of MCA ‎, Dayananda Sagar College of ‎Engineering ‎, Bangalore
    • Dr. Samitha Khaiyum Professor ‎Department of MCA ‎Dayananda Sagar College of ‎Engineering ‎, Bangalore
    • Yashaswini D. S Department of MCA ‎Dayananda Sagar College of ‎Engineering ‎, Bangalore
    • Yadhunandan G. N Department of MCA ‎Dayananda Sagar College of ‎Engineering ‎, Bangalore
    • Yarramreddy Sai Kumar Reddy Department of MCA ‎Dayananda Sagar College of ‎Engineering ‎, Bangalore
    • Yogeshwar S Department of MCA ‎Dayananda Sagar College of ‎Engineering ‎, Bangalore
    https://doi.org/10.14419/3a4djt23

    Received date: May 27, 2025

    Accepted date: June 24, 2025

    Published date: July 7, 2025

  • Cloud Security; Cyberattack Detection; Feature Engineering, DDoS Defense; and Pearson ‎Correlation Analysis

  • Abstract

    Cloud computing infrastructures are often targeted by hacktivists due to their relatively ‎insecure service and delivery paradigms. This article addresses common attack vectors, such ‎as ransomware, insider threats, API breaches, and data leaks, that, if ignored, might ‎jeopardize sensitive data and interfere with important work. We provide a new method based ‎on correlation-based feature selection for identifying fraudulent activities in cloud systems. ‎Using Pearson correlation analysis, we drastically cut down on redundant features on the ‎security dataset, yielding promising results for threat identification. Our feature selection ‎method's effectiveness is empirically supported, and we demonstrate that the classification ‎algorithms perform better when using the improved tool of the optimized data set than when ‎using the original feature set. In this research, a unique approach to intelligent data pre-‎processing for cloud security enhancement is presented‎.

  • References

    1. R.M. Аlguliev, F.C. Abdullayeva, “An investigation and analysis of security problems of the cloud computing,” Problems of Information Technol-ogy, 2013, №1(7), pp. 3-14.
    2. ‘The Treacherous Twelve’ Cloud Computing Top Threats in 2016, https://cloudsecurityalliance.org/artifacts/thetreacherous- twelvecloud- compu-ting-topthreats-in-2016/
    3. M. Aamir, S.M. Zaidi, “Detecting DDoS attacks using feature engineering, machine learning, the framework, and performance assessment The In-ternational Journal of Information Security, 2019, vol. 18, pp. 761- 785. https://doi.org/10.1007/s10207-019-00434-1.
    4. IEEE 4-th International Conference on Network and System Security, "Adaptive Clustering with Feature Ranking for DDoS Attacks Detection," L. Zi, J. Yearwood, X.W. Wu, 2010, pp. 282286.
    5. G. Chandrashekar, F. Sahin, “A survey on feature selection methods,” Computers and Electrical Engineering, 2014, vol. 40, no. 1, pp. 16- 28. https://doi.org/10.1016/j.compeleceng.2013.11.024.
    6. R.K. Deka, D.K. Bhattacharya, J.K. Kalita, “Active utilizing ranked learning to identify DDoS attacks features,” Computer Communications, 2019, vol. 145, pp. 203-222. https://doi.org/10.1016/j.comcom.2019.06.010.
    7. F.J. Abdullayeva, “Advanced Cloud computing persistent threat assault detection technique based on softmax regression and autoencoder algo-rithm,” Array, vol. 10, pp. 1-11.
    8. I. Guyon, A. Elisseeff, “An introduction to variable and feature selection,” Journal of Machine Learning Research, 2003, vol. 3, pp. 1157-1182.
    9. R. Battiti, “IEEE Transactions on Neural Networks, 1994, Vol. 5, no. 4, pp. Using mutual information to select features in supervised neural net learning 537-550”.r https://doi.org/10.1109/72.298224.
    10. CSE-CIC-IDS2018 on AWS, https://www.unb.ca/cic/datasets/ids- 2018.html
    11. HTTP DATASET CSIC 2010, Information Security Institute
    12. Alaigwu, B. E., & Chiroma, H. (2021). A systematic review of cloud computing security: Issues and challenges. Journal of Network and Computer Applications, 176, 102918.
    13. Hameed, S., & Khan, F. (2022). A hybrid feature selection approach for intrusion detection in cloud environments. Future Generation Computer Systems, 127, 345–357.
    14. Moustafa, N., Creech, G., Slay, J., & Turnbull, B. (2020). Big data analytics for intrusion detection: Advances, challenges, and opportunities. Fu-ture Generation Computer Systems, 95, 476 -489.
    15. Singh, S., Chana, I., & Buyya, R. (2020). Agile cloud security service composition for proactive intrusion detection. IEEE Transactions on Cloud Computing, 9(2), 637–650.
    16. Zhang, H., & Wu, S. (2021). Zero-day attack detection in cloud environments using ensemble learning techniques. IEEE Access, 9, 78945–78955.
    17. Shafiq, M. O., Yu, X., Bashir, A. K., & Chaudhry, S. A. (2023). AI-driven DDoS detection using hybrid deep learning models in multi-cloud archi-tectures. Computers & Security, 126, 103013.
    18. Alsaedi, N., & Moustafa, N. (2021). A novel graph-based feature selection technique for cyberattack detection in cloud networks. Journal of In-formation Security and Applications, 57, 102703.
    19. Sahu, A. K., Yadav, D. K., & Pateriya, R. K. (2020). A feature selection based ensemble classifier for effective intrusion detection. Procedia Com-puter Science, 167, 2350–2359. https://doi.org/10.1016/j.procs.2020.03.289.

  • Downloads

  • How to Cite

    GV, smitha, Khaiyum , D. S. ., S, Y. D. ., N, Y. G. ., Reddy, Y. S. K. ., & S, Y. . (2025). Identifying Cyberattacks in Cloud ‎Computing Service Frameworks Through ‎Correlation-Driven Feature. International Journal of Basic and Applied Sciences, 14(2), 645-650. https://doi.org/10.14419/3a4djt23