Scholarlink

This work enhances Cyber Threat Intelligence (CTI) by integrating machine learning with passive monitoring systems, including network telescopes and Internet Background Radiation (IBR). By analyzing unsolicited traffic and leveraging non-stationary autoregressive models, the proposed model improves threat detection accuracy for malware, botnets, and DDoS attacks. Results demonstrate significant advancements in identifying port scanning and botnet activity compared to traditional CTI methods. The work underscores the value of AI-driven automation and predictive analytics for scalable, cost-effective cybersecurity solutions, highlighting future research opportunities in broader IBR applications and enhanced automation.

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

Machine Learning-Driven Cyber Threat Intelligence: A Study on Anomalous Network Traffic Patterns

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Tarun Pandey,
  • V. Anil Kumar

摘要

This work enhances Cyber Threat Intelligence (CTI) by integrating machine learning with passive monitoring systems, including network telescopes and Internet Background Radiation (IBR). By analyzing unsolicited traffic and leveraging non-stationary autoregressive models, the proposed model improves threat detection accuracy for malware, botnets, and DDoS attacks. Results demonstrate significant advancements in identifying port scanning and botnet activity compared to traditional CTI methods. The work underscores the value of AI-driven automation and predictive analytics for scalable, cost-effective cybersecurity solutions, highlighting future research opportunities in broader IBR applications and enhanced automation.