Scholarlink

<p>The rapid advancement of technology has led to the widespread adoption of robotic systems in critical domains such as healthcare, defense, and industrial automation. However, this increased connectivity introduces significant cybersecurity challenges, making robotic systems vulnerable to potential intrusions and cyberattacks. To address these concerns, this study proposes a novel Intrusion Detection System tailored for securing Internet-of-Things based robotic systems. The proposed framework is designed to detect malicious network traffic in real-time, ensuring secure communication and system integrity. The implementation involves real-time traffic monitoring and analysis using a newly developed dataset, ROSIDS23, along with the benchmark NSL-KDD and CICIDS2018 datasets. Experimental validation is conducted on a testbed comprising AlphaBot2 robotic platforms, Raspberry Pi, and a server machine, where captured network traffic is preprocessed and analyzed using machine learning-based classification techniques. The results demonstrate that the proposed framework effectively differentiates between normal and attack traffic, achieving a peak accuracy of 99.38%. These findings highlight the potential of the proposed IDS framework in enhancing the cybersecurity resilience of robotic systems against evolving cyber threats.</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

A real-time intelligent intrusion detection framework for robotic system cybersecurity

  • 期刊论文

  • 发表日期：

    2025年12月18日

查看全文
  • Narinder Verma,
  • Neerendra Kumar,
  • Khalid K. Almuzaini,
  • Anurag Sinha,
  • Syed Abid Hussain

摘要

The rapid advancement of technology has led to the widespread adoption of robotic systems in critical domains such as healthcare, defense, and industrial automation. However, this increased connectivity introduces significant cybersecurity challenges, making robotic systems vulnerable to potential intrusions and cyberattacks. To address these concerns, this study proposes a novel Intrusion Detection System tailored for securing Internet-of-Things based robotic systems. The proposed framework is designed to detect malicious network traffic in real-time, ensuring secure communication and system integrity. The implementation involves real-time traffic monitoring and analysis using a newly developed dataset, ROSIDS23, along with the benchmark NSL-KDD and CICIDS2018 datasets. Experimental validation is conducted on a testbed comprising AlphaBot2 robotic platforms, Raspberry Pi, and a server machine, where captured network traffic is preprocessed and analyzed using machine learning-based classification techniques. The results demonstrate that the proposed framework effectively differentiates between normal and attack traffic, achieving a peak accuracy of 99.38%. These findings highlight the potential of the proposed IDS framework in enhancing the cybersecurity resilience of robotic systems against evolving cyber threats.