Scholarlink

In the rapidly evolving digital landscape, the proliferation of the Internet of Things (IoT) presents considerable efficiency and connectivity. However, this expansion also brings significant cybersecurity challenges, particularly through volume-based attacks (VBAs) that aim to overwhelm systems with sheer data volume. This paper studies the unique characteristics and impacts of VBAs within IoT networks, emphasizing the necessity for advanced detection strategies to protect interconnected devices. Utilizing a comparative analytical approach, we examine the efficacy of Support Vector Machines (SVM) and Naive Bayes classifiers in identifying and countering these threats. Our findings reveal that SVM, with an accuracy of 87.7%, significantly outperforms Naive Bayes, which achieves 74.3% accuracy.

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

SVM Enhanced Detection of Volume-Based Attacks in IoT Networks

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ali Al-Sinayyid,
  • Sasidhar Kadiyala,
  • Rohith Reddy Battula,
  • Venkatesh Mannuru,
  • Timothy Sanford,
  • Alexander Sanchez

摘要

In the rapidly evolving digital landscape, the proliferation of the Internet of Things (IoT) presents considerable efficiency and connectivity. However, this expansion also brings significant cybersecurity challenges, particularly through volume-based attacks (VBAs) that aim to overwhelm systems with sheer data volume. This paper studies the unique characteristics and impacts of VBAs within IoT networks, emphasizing the necessity for advanced detection strategies to protect interconnected devices. Utilizing a comparative analytical approach, we examine the efficacy of Support Vector Machines (SVM) and Naive Bayes classifiers in identifying and countering these threats. Our findings reveal that SVM, with an accuracy of 87.7%, significantly outperforms Naive Bayes, which achieves 74.3% accuracy.