Hybrid intrusion detection model based on a designed autoencoder

Hou, Yuluo; Guo, Jinhong; Xu, Jie; Liu, Renting; Xiang, Xin

doi:10.1007/s12652-022-04350-6

Cited by 2 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hou et al 106 introduce a novel autoencoder model termed NAE, designed with a nonsymmetric architecture. The encoder within NAE effectively captures intricate and compressed representations of network traffic, while the decoder excels in reconstructing input data.…”

Section: Discussionmentioning

confidence: 99%

Botnet‐based IoT network traffic analysis using deep learning

Singh,

Hoque,

Singh

et al. 2023

Security and Privacy

View full text Add to dashboard Cite

IoT networks are increasingly being connected to a wide range of devices, and the number of devices connected has significantly increased in recent years. As a consequence, the number of vulnerabilities to IoT networks has also been increasing tremendously. In IoT networks, botnet‐based Distributed Denial of Service attack is challenging due to its dynamic behavior. The sensors and actuators connected to IoT networks are low‐powered and have less memory. Because of their inherent vulnerability, IoT devices can always be compromised by an attacker and be used to form a large botnet. A detailed analysis of IoT botnet attacks is presented in this article, along with statistics and the architectures of the botnet. We also survey the existing literature on IoT botnet traffic analysis and present a taxonomy of attack detection methods. We particularly focus on deep learning‐based methods and conduct a comparative study to evaluate their performance on IoT traffic analysis. We identify the current issues and research challenges in this field, and we conclude by highlighting some future research directions.

show abstract

Section: Discussionmentioning

confidence: 99%