Scholarlink

With the rise of interconnected devices and increasing cyber threats, robust network security is crucial. This paper explores “Network Intrusion Detection Systems Using AI-Driven Techniques,” leveraging the UNSW_NB15 dataset and the Random Forest algorithm to achieve 83.68% accuracy and an F1-Score of 83.14%. The system detects anomalies in real-time, features a user-friendly interface, and ensures scalability across platforms. By analyzing network traffic attributes, it effectively identifies threats like DDoS attacks with minimal false positives. Extensive evaluation highlights its robustness and adaptability in real-world scenarios. This research highlights the promise of artificial intelligence-based methods in bolstering network security and establishes a foundation for future improvements in systems designed to detect intrusions.

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

Real-Time Network Intrusion Detection System with Machine Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Mehaboob Mujawar,
  • Aasheesh Raizada

摘要

With the rise of interconnected devices and increasing cyber threats, robust network security is crucial. This paper explores “Network Intrusion Detection Systems Using AI-Driven Techniques,” leveraging the UNSW_NB15 dataset and the Random Forest algorithm to achieve 83.68% accuracy and an F1-Score of 83.14%. The system detects anomalies in real-time, features a user-friendly interface, and ensures scalability across platforms. By analyzing network traffic attributes, it effectively identifies threats like DDoS attacks with minimal false positives. Extensive evaluation highlights its robustness and adaptability in real-world scenarios. This research highlights the promise of artificial intelligence-based methods in bolstering network security and establishes a foundation for future improvements in systems designed to detect intrusions.