Scholarlink

<p>As cybersecurity is becoming a prominent domain, it is an imperative to provide real-time anomaly detection for early threat detection and to keep networks safe. In this paper, an optimized hybrid neural network-framework is proposed to detect anomalies at several attack vectors with high efficacy. The framework comprises convolutional neural network equipped with long-short term memory (CNN-LSTM) for temporal and spatial representation of data. As the system accommodates new data and keeps on learning, it adjusts itself becoming a significant mean in counteracting against emerging threats with less latency in detection. In order to verify the efficiency and robustness of the proposed framework, a series of real-time simulation is designed using key performance metrics such as detection rate, false alarm rate and processing time. The results show higher improvement in accuracy and speed of anomaly detection, which makes the framework a useful instrument to reinforce cybersecurity defense during real-time scenarios.</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

Designing a hybrid neural network framework for real-time anomaly detection in cybersecurity applications

  • 期刊论文

  • 发表日期：

    2025年3月26日

查看全文
  • Aaditya Jain,
  • Waleed M. Ead,
  • Mohammed Alshahrani,
  • Jawaher Suliman Altamimi,
  • Fawaz Aklan,
  • Shaza Dawood Rihan

摘要

As cybersecurity is becoming a prominent domain, it is an imperative to provide real-time anomaly detection for early threat detection and to keep networks safe. In this paper, an optimized hybrid neural network-framework is proposed to detect anomalies at several attack vectors with high efficacy. The framework comprises convolutional neural network equipped with long-short term memory (CNN-LSTM) for temporal and spatial representation of data. As the system accommodates new data and keeps on learning, it adjusts itself becoming a significant mean in counteracting against emerging threats with less latency in detection. In order to verify the efficiency and robustness of the proposed framework, a series of real-time simulation is designed using key performance metrics such as detection rate, false alarm rate and processing time. The results show higher improvement in accuracy and speed of anomaly detection, which makes the framework a useful instrument to reinforce cybersecurity defense during real-time scenarios.