A multilayer deep autoencoder approach for cross layer IoT attack detection using deep learning algorithms

一种基于深度学习算法的多层深度自编码器跨层物联网攻击检测方法

阅读:1

Abstract

Cybersecurity professionals depend on multi-layered techniques to find even the most minor anomalies that can point to possible attacks given the complexity of network data. Modern threat environment concerns include feature representation, scalability, and flexibility demand for improved techniques. This work presents the Multi-Layer Deep Autoencoder (M-LDAE), especially tailored for cross-layer IoT threat detection, to solve these difficulties. Specifically designed for cross-layer based Internet of Things (IoT) attack detection, the Multi-Layered Deep Auto Encoder (M-LDAE) is introduced in the present research to overcome these challenges. With the use of deep autoencoders hierarchical simplification capabilities, M-LDAE is able to extract latent representations that contain both global and local attributes. This technology effectively safeguards against various cyber threats, including Man-in-the-Middle attacks at the network layer and Distributed Denial of Service (DDoS) attacks at the transport layer of IoT networks. To improve detection and adapt to emerging attack methods, the M-LDAE system employs deep learning algorithms such as RNNs, GNNs, and TCNs. This research proves that M-LDAE can adapt to new attack vectors, enhance detection accuracy, and reduce false positives through extensive simulations, using benchmark datasets and real-world scenarios. A new paradigm for cross-layer based IoT attack detection is presented in this paper, which provides a flexible and robust solution for complete cybersecurity across different IoT domains and thereby improves the field of cyber threat identification.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。