Malicious traffic segregation using hunger game jellyfish optimisation in IoT-cloud
Sunil Sonawane, Reshma R. Gulwani, Pooja Sharma · International Journal of Grid and Utility Computing · 2024
The extensive growth rate in the Internet of Things (IoT) has acquired a huge focus on cybercriminals and the increasing count of cyber-attacks on IoT devices made it a complex process. Here, a new deep learning-assisted model is developed in cloud-IoT for malicious traffic segregation. Firstly, IoT cloud simulation is done and the data is routed to the Base Station (BS). Routing is implemented with Hunger Game Jellyfish Optimisation (HGJO), where the route is determined based on fitness function. Here, the malicious traffic segregation is executed at BS. The log files are supplied to data pre-processing and feature selection is implemented with Pearson correlation. The malicious traffic segregation is implemented using SpinalNet, which is trained using HGJO. The HGJO is produced by combining the Hunger Games Search (HGS) and Jellyfish Search (JS). The HGJO-SpinalNet provided an elevated accuracy of 91.4%, sensitivity of 91.2% and specificity of 92.1%.