Scholarlink

The fast-growing IoT networks have raised security concerns that call for strong and flexible Intrusion Detection Systems (IDS). Recent Hybrid Deep Learning models for Intrusion Detection Systems (IDS) based on the Internet of Things are investigated in this review together with their efficiency in identifying changing cyber threats. Discussed are important issues include standardizing, interoperability, security, scalability, and edge artificial intelligence deployment. Future directions of research centre on scalable big data analytics, lightweight artificial intelligence for edge computing, and privacy-preserving methods. Dealing with these issues will improve IDS performance, so guaranteeing a stronger IoT ecosystem against new cyber risks.

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

A Review About a Reliable and Safe Intrusion Detection System in an Internet of Things Context: An Emerging Hybrid Deep Learning Model with Potential Directions for Future Research

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Vaidehi Amey Dinkar,
  • Priyank D. Doshi

摘要

The fast-growing IoT networks have raised security concerns that call for strong and flexible Intrusion Detection Systems (IDS). Recent Hybrid Deep Learning models for Intrusion Detection Systems (IDS) based on the Internet of Things are investigated in this review together with their efficiency in identifying changing cyber threats. Discussed are important issues include standardizing, interoperability, security, scalability, and edge artificial intelligence deployment. Future directions of research centre on scalable big data analytics, lightweight artificial intelligence for edge computing, and privacy-preserving methods. Dealing with these issues will improve IDS performance, so guaranteeing a stronger IoT ecosystem against new cyber risks.