Scholarlink

<p>Cybersecurity plays a crucial role in safeguarding&#xa0;digital infrastructures from ever-changing threats. Besides, it guarantees that critical data and systems are always protected, secure, and available. An Intrusion Detection System (IDS) keeps an eye on network traffic&#xa0;and&#xa0;system operations for signs of unauthorized access or malware activity. However, outdated methods typically generate false alarms&#xa0;and&#xa0;have quite low detection accuracy. To address these issues, this work proposes a robust cybersecurity Framework with Progressive Graph Convolutional Networks for Advanced Intrusion Detection and Classification of Sophisticated Cyber Attacks (CSF-PGCN-AID-SCA). The framework integrates an Adaptive Two-Stage Unscented Kalman Filter (ATSUKF) for data pre-processing, Tasmanian Devil Optimization (TDO), a meta-heuristic inspired by the hunting and foraging behavior of Tasmanian devils, is applied to select the most relevant feature and Progressive Graph Convolutional Networks (PGCN) for accurate intrusion detection and attack classification. The framework is implemented in Python and evaluated utilizing the NSL-KDD dataset. The proposed method achieves 8.9–22.5% development in key performance metrics, like accuracy, F1-score, recall, precision, and specificity, outperforming existing techniques such as A fully streaming big data framework for cyber security related to an optimized deep learning algorithm (BDF-CS-CNN), the detection of real-time malicious intrusions and attacks in IoT-enabled cyber security infrastructures (MIA-IoT-CSI-RNN), and the application of the African Vulture optimization algorithm related to deep learning for cyber security intrusion detection (CS-ID-AVOA). This approach provides a scalable and efficient solution for real-time detection of cyber threats, enhancing IDS reliability in complex network 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

Developing a robust cyber security framework by progressive graph convolutional networks for advanced intrusion detection and comprehensive classification of sophisticated cyber attacks

  • 期刊论文

  • 发表日期：

    2026年6月23日

查看全文
  • Amita Kathole,
  • Sukhvinder Singh Dari,
  • Dharmesh Dhabliya,
  • Parikshit N. Mahalle,
  • Jambi Ratna Raja Kumar

摘要

Cybersecurity plays a crucial role in safeguarding digital infrastructures from ever-changing threats. Besides, it guarantees that critical data and systems are always protected, secure, and available. An Intrusion Detection System (IDS) keeps an eye on network traffic and system operations for signs of unauthorized access or malware activity. However, outdated methods typically generate false alarms and have quite low detection accuracy. To address these issues, this work proposes a robust cybersecurity Framework with Progressive Graph Convolutional Networks for Advanced Intrusion Detection and Classification of Sophisticated Cyber Attacks (CSF-PGCN-AID-SCA). The framework integrates an Adaptive Two-Stage Unscented Kalman Filter (ATSUKF) for data pre-processing, Tasmanian Devil Optimization (TDO), a meta-heuristic inspired by the hunting and foraging behavior of Tasmanian devils, is applied to select the most relevant feature and Progressive Graph Convolutional Networks (PGCN) for accurate intrusion detection and attack classification. The framework is implemented in Python and evaluated utilizing the NSL-KDD dataset. The proposed method achieves 8.9–22.5% development in key performance metrics, like accuracy, F1-score, recall, precision, and specificity, outperforming existing techniques such as A fully streaming big data framework for cyber security related to an optimized deep learning algorithm (BDF-CS-CNN), the detection of real-time malicious intrusions and attacks in IoT-enabled cyber security infrastructures (MIA-IoT-CSI-RNN), and the application of the African Vulture optimization algorithm related to deep learning for cyber security intrusion detection (CS-ID-AVOA). This approach provides a scalable and efficient solution for real-time detection of cyber threats, enhancing IDS reliability in complex network environments.