Cuckoo Search-Optimized Deep CNN for Enhanced Cyber Security in IoT Networks

Brij B. Gupta, Akshat Gaurav, Varsha Arya, Razaz Waheeb Attar, Shavi Bansal, Ahmed Alhomoud, Kwok Tai Chui

Research output: Contribution to journalArticlepeer-review

Abstract

Phishing attacks seriously threaten information privacy and security within the Internet of Things (IoT) ecosystem. Numerous phishing attack detection solutions have been developed for IoT; however, many of these are either not optimally efficient or lack the lightweight characteristics needed for practical application. This paper proposes and optimizes a lightweight deep-learning model for phishing attack detection. Our model employs a two-fold optimization approach: first, it utilizes the analysis of the variance (ANOVA) F-test to select the optimal features for phishing detection, and second, it applies the Cuckoo Search algorithm to tune the hyperparameters (learning rate and dropout rate) of the deep learning model. Additionally, our model is trained in only five epochs, making it more lightweight than other deep learning (DL) and machine learning (ML) models. The proposed model achieved a phishing detection accuracy of 91%, with a precision of 92% for the’normal’ class and 91% for the ‘attack’ class. Moreover, the model’s recall and F1-score are 91% for both classes. We also compared our approach with traditional DL/ML models and past literature, demonstrating that our model is more accurate. This study enhances the security of sensitive information and IoT devices by offering a novel and effective approach to phishing detection.

Original languageEnglish
Pages (from-to)4109-4124
Number of pages16
JournalComputers, Materials and Continua
Volume81
Issue number3
DOIs
Publication statusPublished - 2024

Keywords

  • ANOVA F-test
  • cable news network (CNN)
  • Cuckoo Search
  • Deep learning
  • IoT
  • phishing

Fingerprint

Dive into the research topics of 'Cuckoo Search-Optimized Deep CNN for Enhanced Cyber Security in IoT Networks'. Together they form a unique fingerprint.

Cite this