SafetyMed: A Novel IoMT Intrusion Detection System Using CNN-LSTM Hybridization

Faruqui, Nuruzzaman; Yousuf, Mohammad Abu; Whaiduzzaman, Md; Azad, AKM; Alyami, Salem A.; Liò, Pietro; Kabir, Muhammad Ashad; Moni, Mohammad Ali

doi:10.3390/electronics12173541

Cited by 21 publications

(9 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the optimization algorithm has been chosen based on their performance through experiment [49] . Analyzing the underlying mathematical models of a CNN and modifying them is an effective way to enhance performance while reducing computational resource consumption [50] . One of the core contributions of this research is the simplicity of the network design and the reduction of the computational cost.…”

Section: Proposed Methodologymentioning

confidence: 99%

Healthcare As a Service (HAAS): CNN-based cloud computing model for ubiquitous access to lung cancer diagnosis

Faruqui,

Yousuf,

Kateb

et al. 2023

Heliyon

Self Cite

View full text Add to dashboard Cite

Section: Proposed Methodologymentioning

confidence: 99%

Healthcare As a Service (HAAS): CNN-based cloud computing model for ubiquitous access to lung cancer diagnosis

Faruqui,

Yousuf,

Kateb

et al. 2023

Heliyon

Self Cite

View full text Add to dashboard Cite

“…The model is trained and evaluated on the CTU-13 dataset and can efficiently identify botnets, achieving 99.6% accuracy. Similarly, the authors in [22] presented a hybrid IDS for the Internet of Medical Things (IoMT). This system combines CNN and LSTM networks and exhibits an average accuracy of 97.63%.…”

Section: Related Workmentioning

confidence: 99%

SkipGateNet: A Lightweight CNN-LSTM Hybrid Model With Learnable Skip Connections for Efficient Botnet Attack Detection in IoT

Alshehri,

Ahmad,

Almakdi

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The rise of Internet of Things (IoT) has led to increased security risks, particularly from botnet attacks that exploit IoT device vulnerabilities. This situation necessitates effective Intrusion Detection Systems (IDS), that are accurate, lightweight, and fast (having less inference time), designed particularly to detect botnet attacks in resource constrained IoT devices. This paper proposes SkipGateNet, a novel deep learning model designed for detecting Mirai and Bashlite botnet attacks in resource constrained IoT and fog computing environments. SkipGateNet is a lightweight, fast model combining 1D-Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) layers. The novelty of this model lies in the integration of 'Learnable Skip Connections'. These connections feature gating mechanisms that enhance detection by focusing on relevant features and ignoring irrelevant ones. They add adaptability to the architecture, performing feature selection and propagating only essential features to deeper layers. Tested on the N-BaIoT dataset, SkipGateNet efficiently detects ten types of botnet attacks, with a remarkable test accuracy of 99.91%. It is also compact (2596.87 KB) and demonstrates a quick inference time of 8.0 milliseconds, suitable for real-time implementation in resource-limited settings. While evaluating its performance, parameters like precision, recall, accuracy, and F1 score were considered, along with statistical reliability measures like Cohen's Kappa Coefficient and Matthews Correlation Coefficient. These highlight its reliability and effectiveness in IoT security challenges. The paper also compares SkipGateNet to existing models and four other deep learning architectures, including two sequential CNN architectures, a simple CNN+LSTM architecture, and a CNN+LSTM with standard skip connections. SkipGateNet surpasses all in accuracy and inference time, demonstrating its superiority in addressing IoT security issues.

show abstract

“…Through the use of a zero-trust security architecture [16], author was able to create an effective intrusion detection system. Over the course of six years, author kept a close eye on the network and made sure that only authorized devices were able to connect.…”

Section: A Related Workmentioning

confidence: 99%

A Comparative Study of Anomaly Detection Techniques for IoT Security Using Adaptive Machine Learning for IoT Threats

Alsalman

2024

IEEE Access

View full text Add to dashboard Cite

Anomaly detection is a critical aspect of various applications, including security, healthcare, and network monitoring. In this study, we introduce FusionNet, an innovative ensemble model that combines the strengths of multiple machine learning algorithms, namely Random Forest, K-Nearest Neighbors, Support Vector Machine, and Multi-Layer Perceptron, for enhanced anomaly detection. FusionNet's architecture leverages the diversity of these algorithms to achieve high accuracy and precision. We evaluate FusionNet's performance on two distinct datasets, Dataset 1 and Dataset 2, and compare it with traditional machine learning models, including SVM, KNN, and RF. The results demonstrate that FusionNet consistently outperforms these models across both datasets in terms of accuracy, precision, recall, and F1 score. On Dataset 1, FusionNet achieves an accuracy of 98.5% and on Dataset 2, it attains an accuracy of 99.5%. FusionNet's remarkable ability to detect anomalies with exceptional accuracy underscores its potential for real-world applications. This study highlights the significance of FusionNet as a robust model for anomaly detection and provides insights into its superior performance over traditional models. The results emphasize the promising prospects of FusionNet in security, healthcare, and other domains where accurate anomaly detection is crucial.

show abstract

SafetyMed: A Novel IoMT Intrusion Detection System Using CNN-LSTM Hybridization

Cited by 21 publications

References 59 publications

Healthcare As a Service (HAAS): CNN-based cloud computing model for ubiquitous access to lung cancer diagnosis

Healthcare As a Service (HAAS): CNN-based cloud computing model for ubiquitous access to lung cancer diagnosis

SkipGateNet: A Lightweight CNN-LSTM Hybrid Model With Learnable Skip Connections for Efficient Botnet Attack Detection in IoT

A Comparative Study of Anomaly Detection Techniques for IoT Security Using Adaptive Machine Learning for IoT Threats

Contact Info

Product

Resources

About