Blockchain enhanced distributed denial of service detection in IoT using deep learning and evolutionary computation

Area of Science:

• Cybersecurity
• Network Security
• Artificial Intelligence

Background:

• The Internet of Things (IoT) faces significant security challenges, particularly Distributed Denial of Service (DDoS) attacks, due to resource-constrained devices.
• Blockchain technology (BC) offers potential decentralized security solutions for IoT vulnerabilities.
• Existing methods struggle to effectively detect and mitigate DDoS threats in complex IoT ecosystems.

Purpose of the Study:

• To propose an effective method for detecting DDoS threats in IoT environments using advanced techniques.
• To enhance the security of IoT applications by leveraging Blockchain and Deep Learning.
• To introduce the Metaheuristic-Optimized Blockchain Framework for Attack Detection using a Deep Learning Model (MOBCF-ADDLM).

Main Methods:

• Utilizing Blockchain technology for decentralized security solutions against DDoS attacks.
• Implementing min-max scaling for data preprocessing and the Aquila Optimizer (AO) for feature selection (FS).
• Employing a Deep Belief Network (DBN) for attack classification, with hyper-parameter optimization by the Red Panda Optimizer (RPO).

Main Results:

• The MOBCF-ADDLM approach demonstrated superior performance in detecting DDoS threats.
• Experiments conducted on BoT-IoT Binary and Multiclass datasets validated the model's effectiveness.
• The proposed method achieved a high accuracy of 99.22%, outperforming existing models.

Conclusions:

• The MOBCF-ADDLM framework provides an effective and accurate solution for DDoS attack detection in IoT systems.
• The integration of Blockchain, Deep Learning, and metaheuristic optimization significantly enhances IoT security.
• This research contributes a robust defense mechanism against prevalent cyber threats in the expanding IoT landscape.