IFACNN: efficient DDoS attack detection based on improved firefly algorithm to optimize convolutional neural...

Area of Science:

• Computer Science
• Network Security
• Artificial Intelligence

Background:

• The proliferation of Internet of Things (IoT) devices has significantly increased network vulnerabilities.
• Distributed Denial of Service (DDoS) attacks pose a major threat to critical network services, often targeting IoT devices.
• Software-Defined Networking (SDN) has emerged as a key technology for managing and securing IoT environments.

Purpose of the Study:

• To propose a novel DDoS attack detection scheme for the software-defined Internet of Things (SD-IoT) environment.
• To enhance the security and real-time monitoring capabilities within SD-IoT networks.
• To address the growing threat of DDoS attacks on interconnected IoT devices.

Main Methods:

• Utilized an improved Firefly Algorithm to optimize a Convolutional Neural Network (CNN) model.
• Developed a DDoS attack detection framework tailored for SD-IoT environments.
• Evaluated the scheme's performance in detecting both DDoS attack behavior and benign traffic.

Main Results:

• The proposed scheme demonstrated high accuracy in detecting DDoS attacks.
• Achieved a detection accuracy exceeding 99% for both malicious (DDoS) and benign network traffic.
• Validated the effectiveness of the optimized CNN within the SD-IoT framework.

Conclusions:

• The developed DDoS detection scheme effectively secures the SD-IoT environment.
• The integration of an optimized CNN with the Firefly Algorithm provides a robust solution for network security.
• The findings highlight the potential of AI-driven approaches for safeguarding IoT ecosystems against sophisticated cyber threats.