A Novel IDS with a Dynamic Access Control Algorithm to Detect and Defend Intrusion at IoT Nodes

Area of Science:

• Cybersecurity
• Computer Networks
• Artificial Intelligence

Background:

• The Internet of Things (IoT) is rapidly expanding, creating a large market attractive to cybercriminals.
• Resource-constrained IoT devices often lack robust cybersecurity features, leading to increased intrusions.
• Existing Intrusion Detection Systems (IDS) struggle to keep pace with the evolving threat landscape in IoT environments.

Purpose of the Study:

• To develop and evaluate a novel Intrusion Detection System (IDS) for the Internet of Things (IoT).
• To enhance IoT security by effectively detecting and defending against a wide range of cyber threats.
• To improve the accuracy and efficiency of intrusion detection in resource-constrained IoT environments.

Main Methods:

• Implementation of a Long Short-Term Memory (LSTM) based Intrusion Detection System (IDS).
• Integration of a Dynamic Access Control (DAC) algorithm for enhanced defense capabilities.
• Mathematical analysis for model selection and optimization of the IDS.

Main Results:

• The proposed LSTM-based IDS achieved a validation accuracy of 97.16%.
• The system demonstrated high performance metrics, with precision, recall, and F1 scores around 97%.
• The IDS successfully identified 14 different types of threats with a detection rate exceeding 98% and a response time under 1.2 seconds.

Conclusions:

• The novel LSTM-based IDS with DAC offers a significant advancement in IoT security.
• The system's high accuracy, broad threat identification, and rapid response time make it a reliable solution for protecting IoT ecosystems.
• Optimized through mathematical analysis, this IDS effectively balances threat detection with minimized false alarms, enhancing overall IoT security.