Scholarlink

<p>The study develops and implements an intelligent system designed to enhance security and maintain high Quality of Service (QoS) in multi-cloud environments. Existing convolutional approaches often struggle to achieve consistent security and service quality, especially in dynamic networks. The goal of the study is to address these challenges by introducing an advanced method for traffic analysis and malicious traffic detection in multi-cloud systems. Conventional methods face limitations in accurately identifying and categorizing hostile traffic, such as Denial-of-Service (DoS) attacks, and in maintaining QoS under attack conditions. The study presents an Integrated Ant Lion Optimized Boosted Gated Recurrent Unit (IANO-BGRU), which integrates ant-lion optimization with a boosted gated recurrent unit. This novel approach enhances the precision of hostile traffic detection and QoS management compared to existing methods. The IANO-BGRU method achieves high accuracy (98%), sensitivity (97%), and specificity (96%) in detecting malicious traffic. It supports a maximum processing velocity of 0.55 Gbit/s, with active and passive response times of 66&#xa0;s and 200&#xa0;s, respectively. The system maintains QoS with only 2.4% violation detection actively and 25% passively, even during attacks. The IANO-BGRU strategy significantly improves cybersecurity and QoS management in multi-cloud settings, offering robust protection against sophisticated threats while ensuring reliable service delivery. The research emphasises the novel IANO-BGRU’s considerable advances in cybersecurity and QoS management, as well as its influence on cloud-based security solutions. This approach sets new benchmarks for intelligent security systems and may greatly enhance the field of cloud-based security solutions.</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

Optimizing security and Qos in multi-cloud platform using a novel approach

  • 期刊论文

  • 发表日期：

    2025年2月19日

查看全文
  • M. S. Nidhya,
  • Nishu Niharika,
  • Vaibhav Kaushik,
  • Lovish Dhingra,
  • Harshit Raichura,
  • Manish Kumar Goyal

摘要

The study develops and implements an intelligent system designed to enhance security and maintain high Quality of Service (QoS) in multi-cloud environments. Existing convolutional approaches often struggle to achieve consistent security and service quality, especially in dynamic networks. The goal of the study is to address these challenges by introducing an advanced method for traffic analysis and malicious traffic detection in multi-cloud systems. Conventional methods face limitations in accurately identifying and categorizing hostile traffic, such as Denial-of-Service (DoS) attacks, and in maintaining QoS under attack conditions. The study presents an Integrated Ant Lion Optimized Boosted Gated Recurrent Unit (IANO-BGRU), which integrates ant-lion optimization with a boosted gated recurrent unit. This novel approach enhances the precision of hostile traffic detection and QoS management compared to existing methods. The IANO-BGRU method achieves high accuracy (98%), sensitivity (97%), and specificity (96%) in detecting malicious traffic. It supports a maximum processing velocity of 0.55 Gbit/s, with active and passive response times of 66 s and 200 s, respectively. The system maintains QoS with only 2.4% violation detection actively and 25% passively, even during attacks. The IANO-BGRU strategy significantly improves cybersecurity and QoS management in multi-cloud settings, offering robust protection against sophisticated threats while ensuring reliable service delivery. The research emphasises the novel IANO-BGRU’s considerable advances in cybersecurity and QoS management, as well as its influence on cloud-based security solutions. This approach sets new benchmarks for intelligent security systems and may greatly enhance the field of cloud-based security solutions.