An intelligent intrusion prediction and prevention system for software defined internet of things cloud networks.

Kranthi, S.; Kanchana, M.; Suneetha, M.

Securing digital data transmission or communication is essential for the growing smart cities. At the same, malicious vulnerabilities are also enhanced to break the security. Hence, securing data in a wireless or innovative environment is challenging. So, the current research article has aimed to design novel chimp-based Auto-encoder Networks (CbAN) for the Software-Defined-Network (SDN) Internet-of-Things (IoT) cloud network. Moreover, the SDN with Distributed-Denial-of-Service (DDoS) attack database has been considered in this research. Initially, the datasets were arranged in the tree structure then the error neglecting process was performed. Consequently, the error-less data is imported from the classification module of the auto-encoder tree. Incorporating the chimp fitness solution has offered a better feature extraction and classification outcome. After classifying the malicious features, it is neglected in the SDN environment. Finally, the proposed novel CbAN scheme has been executed in the python platform and has earned outstanding results than the previous work by yielding the highest intrusion forecasting accuracy.

INTERNET of things; DATA transmission systems; SYSTEMS software; SMART cities; DATABASES; INTELLIGENT networks

Peer-to-Peer Networking & Applications, 2023, Vol 16, Issue 1, p210

1936-6442

Academic Journal

10.1007/s12083-022-01374-9