Scholarlink

Utilizing deep learning techniques for time-series analysis is pivotal in strengthening network security anomaly detection. This approach capitalizes on the inherent temporal dynamics within network data, empowering deep learning models like RNNs, LSTMs, and CNNs to discern intricate temporal relationships swiftly. These models bolster security measures by promptly identifying anomalies and potential breaches. By training on historical data, they learn normal patterns and recognize deviations in real-time network traffic. The paper emphasizes the creation of resilient models differentiating standard and irregular activities, contributing to proactive security measures within network infrastructures.

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

Revolutionizing Network Security: Harnessing Deep Learning for Anomaly Detection in Time-Series Data

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • G. Lakshmi Praveena,
  • R. Usha,
  • T. Pratyusha,
  • Ganapavarapu Surekha,
  • Pokuri Deepika,
  • T. Jyotsna

摘要

Utilizing deep learning techniques for time-series analysis is pivotal in strengthening network security anomaly detection. This approach capitalizes on the inherent temporal dynamics within network data, empowering deep learning models like RNNs, LSTMs, and CNNs to discern intricate temporal relationships swiftly. These models bolster security measures by promptly identifying anomalies and potential breaches. By training on historical data, they learn normal patterns and recognize deviations in real-time network traffic. The paper emphasizes the creation of resilient models differentiating standard and irregular activities, contributing to proactive security measures within network infrastructures.