Internet usage became increasingly ubiquitous. The concern regarding security and privacy has become essential for Internet users. As the usage of the Internet increases the number of cyber‐attacks also increases substantially. Intrusion detection is one of the challenging aspects of network security. Efficient intrusion detection is crucial for every organization to mitigate the vulnerability. This paper presents a novel intrusion detection system to detect malicious attacks targeted at a smart environment. The proposed Intrusion detection method uses a correlation tool and a random forest method to detect the predominant independent variables for improvising neural‐based attack classifier. To detect a malicious attack, a shallow neural network and an optimized neural‐based classifier are presented. The designed intrusion detection system has experimented on the KDDCUP99 dataset. The experimental results reveal that the performance of the proposed intrusion detection system is superior in terms of quantitative metrics. Thus, the proposed system can be deployed in the IoT and wireless networks to detect cyber‐attacks.

中文翻译：

---

使用优化的深度神经网络架构的入侵检测系统

互联网的使用变得越来越普遍。对安全性和隐私的关注已成为Internet用户必不可少的。随着互联网使用的增加，网络攻击的数量也大大增加。入侵检测是网络安全中具有挑战性的方面之一。高效的入侵检测对于每个组织缓解漏洞至关重要。本文提出了一种新颖的入侵检测系统，可以检测针对智能环境的恶意攻击。提出的入侵检测方法使用相关工具和随机森林方法来检测主要的独立变量，以改进基于神经的攻击分类器。为了检测恶意攻击，提出了一种浅层神经网络和一种优化的基于神经的分类器。设计的入侵检测系统已经在KDDCUP99数据集上进行了实验。实验结果表明，所提出的入侵检测系统的性能在定量指标方面是优越的。因此，建议的系统可以部署在物联网和无线网络中以检测网络攻击。