Scholarlink

Intrusion detection systems are playing a critical role in protecting networks against advanced cyber threats. However, the discovery of unknown attacks is challenging, where these are the attacks which are completely novel and have no patches. In this paper, the authors present an unsupervised intrusion detection system that successfully detects zero-day attacks by applying unsupervised deep learning and machine learning methods. The proposed system was tested through extensive experimentation on famous benchmark datasets UNSW NB-15 and NSL-KDD. The experimentation outcome reflects the efficacy of the proposed approach in spotting zero-day attacks. Comparison with other related works showed that the proposed IDS system outperforms the existing systems.

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

Unsupervised Intrusion Detection System for Zero-Day Attack Detection Using Machine Learning and Deep Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Sirisha Surepalli,
  • Nerella Sameera

摘要

Intrusion detection systems are playing a critical role in protecting networks against advanced cyber threats. However, the discovery of unknown attacks is challenging, where these are the attacks which are completely novel and have no patches. In this paper, the authors present an unsupervised intrusion detection system that successfully detects zero-day attacks by applying unsupervised deep learning and machine learning methods. The proposed system was tested through extensive experimentation on famous benchmark datasets UNSW NB-15 and NSL-KDD. The experimentation outcome reflects the efficacy of the proposed approach in spotting zero-day attacks. Comparison with other related works showed that the proposed IDS system outperforms the existing systems.