Scholarlink

<p>Cloud computing has become a core component of modern information technology, widely adopted by enterprises, organizations, and businesses for its cost-effective, flexible, and scalable infrastructure. However, the growing reliance on cloud services has also increased the risks of network threats, making the security and privacy of cloud data a critical concern. To address this, this paper introduces a novel anomaly detection and access control framework, termed the Artificial Sine Cosine fluctuation-based Gannet Optimized Authentication scheme. The proposed model adapts dynamically to evolving traffic patterns while minimizing false positives. It leverages multiple benchmark intrusion detection datasets and undergoes comprehensive preprocessing, including cleaning, transformation, reduction, and normalization, to ensure high-quality input. For feature extraction, an Improved Linear Discriminant Analysis is employed to reduce dimensionality while retaining the most significant attributes. Anomalies are classified using an Artificial Neural Network, and its hyperparameters are optimized with the Sine Cosine fluctuation-based Gannet Optimization Algorithm, effectively balancing exploration and exploitation during training. Following classification, data are segregated into confidential and non-confidential categories. Confidential data undergoes encryption and decryption to maintain privacy, while Multifactor Authentication ensures that only authorized users gain access. Experimental evaluations across standard datasets confirm that the proposed model achieves superior detection performance, with a classification accuracy of 98.80% and an F1-score of 97.77%. These results confirm that the proposed framework provides a robust, efficient, and trustworthy solution for anomaly detection and access control in cloud environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimization-based machine learning for authenticated cloud security using anomaly detection and classification

  • 期刊论文

  • 发表日期：

    2026年2月16日

查看全文
  • R. Usharani,
  • E. Nirmala,
  • N. Arockia Rosy,
  • P. Jagadeesan

摘要

Cloud computing has become a core component of modern information technology, widely adopted by enterprises, organizations, and businesses for its cost-effective, flexible, and scalable infrastructure. However, the growing reliance on cloud services has also increased the risks of network threats, making the security and privacy of cloud data a critical concern. To address this, this paper introduces a novel anomaly detection and access control framework, termed the Artificial Sine Cosine fluctuation-based Gannet Optimized Authentication scheme. The proposed model adapts dynamically to evolving traffic patterns while minimizing false positives. It leverages multiple benchmark intrusion detection datasets and undergoes comprehensive preprocessing, including cleaning, transformation, reduction, and normalization, to ensure high-quality input. For feature extraction, an Improved Linear Discriminant Analysis is employed to reduce dimensionality while retaining the most significant attributes. Anomalies are classified using an Artificial Neural Network, and its hyperparameters are optimized with the Sine Cosine fluctuation-based Gannet Optimization Algorithm, effectively balancing exploration and exploitation during training. Following classification, data are segregated into confidential and non-confidential categories. Confidential data undergoes encryption and decryption to maintain privacy, while Multifactor Authentication ensures that only authorized users gain access. Experimental evaluations across standard datasets confirm that the proposed model achieves superior detection performance, with a classification accuracy of 98.80% and an F1-score of 97.77%. These results confirm that the proposed framework provides a robust, efficient, and trustworthy solution for anomaly detection and access control in cloud environments.