Scholarlink

<p>A novel innovative approach is introduced in this research for identifying Distributed Denial of Service (DDoS) attack in Internet of Things (IoT) networks using Piecewise Gazelle Optimization Algorithm (PGOA) and Quantum Graph Neural Network (QGNNs) classifier. Recognizing the exposure of IoT networks to DDoS attacks, which disrupts critical services and jeopardize sensitive data, this research emphasizes the need for an effective detection method. Thereby, the PGOA, inspired by the strategic movement of gazelles and enhanced with Piecewise Chaotic Map is proposed to effectively navigate and select optimal features from complex IoT data sets. This method aims to overcome limitations of traditional feature selection by introducing controlled randomness, enhancing the exploration of the solution space. Moreover, the QGNNs, which merge quantum computing principles with graph neural networks, efficiently handle the intricate data structures characteristic of IoT networks, thereby improving accuracy and speed of DDoS attack detection. It is also effective in quick processing of complex graph-structured data along with providing a higher degree of precision in classification tasks. This approach marks a significant step in bolstering IoT network security against DDoS threats, underscoring the importance of innovative solutions to meet evolving cybersecurity challenges.</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

Quantum-Enhanced IoT Security Against DDoS Attacks Integrating Piecewise Gazelle Optimization and Graph Neural Networks

  • 期刊论文

  • 发表日期：

    2025年7月19日

查看全文
  • R. Sahila Devi,
  • R. Bharathi,
  • P. Krishna Kumar

摘要

A novel innovative approach is introduced in this research for identifying Distributed Denial of Service (DDoS) attack in Internet of Things (IoT) networks using Piecewise Gazelle Optimization Algorithm (PGOA) and Quantum Graph Neural Network (QGNNs) classifier. Recognizing the exposure of IoT networks to DDoS attacks, which disrupts critical services and jeopardize sensitive data, this research emphasizes the need for an effective detection method. Thereby, the PGOA, inspired by the strategic movement of gazelles and enhanced with Piecewise Chaotic Map is proposed to effectively navigate and select optimal features from complex IoT data sets. This method aims to overcome limitations of traditional feature selection by introducing controlled randomness, enhancing the exploration of the solution space. Moreover, the QGNNs, which merge quantum computing principles with graph neural networks, efficiently handle the intricate data structures characteristic of IoT networks, thereby improving accuracy and speed of DDoS attack detection. It is also effective in quick processing of complex graph-structured data along with providing a higher degree of precision in classification tasks. This approach marks a significant step in bolstering IoT network security against DDoS threats, underscoring the importance of innovative solutions to meet evolving cybersecurity challenges.