Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India

Research Article

Machine Learning For Predicting Cloud Security

Download65 downloads
  • @INPROCEEDINGS{10.4108/eai.23-11-2023.2343236,
        author={Kiruthika K and Maheshkumar R S and Sridharan S and Jeevananthan V},
        title={Machine Learning For Predicting Cloud Security},
        proceedings={Proceedings of the 1st International Conference on Artificial Intelligence, Communication, IoT, Data Engineering and Security, IACIDS 2023, 23-25 November 2023, Lavasa, Pune, India},
        publisher={EAI},
        proceedings_a={IACIDS},
        year={2024},
        month={3},
        keywords={cloud computing cloud security machine learning systematic literature review data privacy ddos mitigation svm j48 future directions},
        doi={10.4108/eai.23-11-2023.2343236}
    }
    
  • Kiruthika K
    Maheshkumar R S
    Sridharan S
    Jeevananthan V
    Year: 2024
    Machine Learning For Predicting Cloud Security
    IACIDS
    EAI
    DOI: 10.4108/eai.23-11-2023.2343236
Kiruthika K1,*, Maheshkumar R S2, Sridharan S2, Jeevananthan V2
  • 1: Associate Professor of Mathematics, K S Rangasamy College of Technology, Tiruchengode
  • 2: Student of Computer Science and Engineering, K S Rangasamy College of Technology, Tiruchengode
*Contact email: kiruthika@ksrct.ac.in

Abstract

The prominence and utilization of Cloud computing are experiencing rapid growth, with numerous organizations making substantial investments in this sector, either for their own advantages or to offer services to external parties.One effective approach to addressing these security challenges in the Cloud is through the application of artificial intelligence (AI) and machine learning (ML) techniques. Machine learning techniques have found application in a variety of methods aimed at preventing or identifying attacks and vulnerabilities within Cloud systems. Within our analysis, we identified 30 distinct machine learning (ML) techniques, some of which were employed in hybrid approaches, while others were used independently.It's worth noting that Support Vector Machine (SVM) and J48 have emerged as the most widely adopted ML algorithms, utilized in both hybrid and standalone models.