Search

In an era dominated by the Internet of Things (IoT), protecting interconnected devices from botnets has become essential. This study introduces an innovative hybrid deep learning model that synergizes LSTM Auto Encoders and Multilayer Perceptrons in detecting botnets in IoTs. The fusion of these technologies facilitates the analysis of sequential data and pattern recognition, enabling the model to detect intricate botnet activities within IoT networks. The proposed model's performance was carefully evaluated on two large IoT traffic datasets, N-BAIoT2018 and UNSW-NB15, where it demonstrated exceptional accuracy of 99.77 % and 99.67 % respectively for botnet detection. These results not only demonstrate the model's superior performance over existing botnet detection systems but also highlight its potential as a robust solution for IoT network security.

In an era dominated by the Internet of Things (IoT), protecting interconnected devices from botnets has become essential. This study introduces an innovative hybrid deep learning model that synergizes LSTM Auto Encoders and Multilayer Perceptrons in detecting botnets in IoTs. The fusion of these technologies facilitates the analysis of sequential data and pattern recognition, enabling the model to detect intricate botnet activities within IoT networks. The proposed model's performance was carefully evaluated on two large IoT traffic datasets, N-BAIoT2018 and UNSW-NB15, where it demonstrated exceptional accuracy of 99.77 % and 99.67 % respectively for botnet detection. These results not only demonstrate the model's superior performance over existing botnet detection systems but also highlight its potential as a robust solution for IoT network security. [ABSTRACT FROM AUTHOR]