IoT Enhancement with Automated Device Identification for Network Security

Sundaram, B. Barani; Pandey, Amit; Janga, Vijaykumar; Wako, Desalegn Aweke; Genale, Assefa Senbato; Karthika, P.

doi:10.1109/icoei53556.2022.9776678

Cited by 4 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental setup was conducted on a machine equipped with an Intel Core i5 processor, 16 GB of RAM, and a 512 GB SSD, running the Microsoft Windows 10 operating system [58]. MATLAB 2020a was selected for simulation purposes to execute the WOA-based anomaly detection as described.…”

Section: Results Discussionmentioning

confidence: 99%

A Hybrid Framework Leveraging Whale Optimization and Deep Learning With Trust-Index for Attack Identification in IoT Networks

Gotarane,

Abimannan,

Hussain

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The rise of smart cities, smart homes, and smart health powered by the Internet of Things (IoT) presents significant challenges in design, deployment, and security. The seamless data processing across a complex network of interconnected devices in unprotected conditions makes it vulnerable to potential breaches, underscoring the need for robust security at various levels of the network. Traditional security methods based on statistics often struggle to comprehend data patterns and provide the desired level of security. This work proposes a novel hybrid framework that combines Whale Optimization and Deep Learning with a trust-index to identify malicious nodes engaging in various attacks such as DoS, DDoS, Drop attack, and Tamper Attacks, thus enhancing IoT node security. The developed framework first calculates a trust-index score for IoT nodes based on drop attack, tamper attack, replay attack, and multiple-max attack. Subsequently, it utilizes the trust index score in the Optimized Neural Network (ONN) model to effectively identify the malicious IoT node. The neural network optimization is achieved through a fitness function that determines optimal weights using the Whale Optimization Algorithm. The proposed framework has been tested across varying network sizes, comprising 100, 500, and 1000 nodes. The resulting outcomes were evaluated against benchmark security methods such as Logical regression (LR),Random Forest (RF), Support Vector Machine (SVM), Bayesian models, ANN, Elephant herding optimization (EHO),and Lion algorithm (LA) using metrics like specificity, sensitivity, accuracy, precision, False Positive Rate (FPR), False Negative Rate (FNR), False Discovery Rate (FDR), Error, F1 score, Matthews Correlation Coefficient (MCC), and Negative Predictive Value (NPV). The results reveal a notable enhancement in accuracy (26.63%, 13.04%, 17.78%, 30.52%, 22.45%, 4.26%, and 2.24%) for a 100node network when compared to the benchmark security methods. Furthermore, the proposed framework consistently demonstrates strong performance even when applied to larger IoT networks with a higher node count.

show abstract

Section: Results Discussionmentioning

confidence: 99%