South Korean researchers develop AI to secure 5G-enabled IIoT environments

Researchers from the Incheon National University (INU) in South Korea have developed artificial intelligence (AI) approach for classifying cyber-attacks in 5G-enabled industrial internet of things (IIoT) system.  

This system can be employed to safeguard real-time connectivity applications, such as smart cities and autonomous vehicles, providing a robust framework for pioneering future advanced security systems to mitigate a range of cybercrime, they said.

According to the researchers, IIoT powered by wireless 5G connectivity and AI holds the ability to analyse critical problems and provide solutions that can improve the operational performance of industries ranging from manufacturing to healthcare, these IIoT systems are also prone to security threats.

As IIoT is getting more popular in industries, it is becoming crucial to develop an efficient system to handle such security concerns. So, a team of multinational researchers led by professor Gwanggil Jeon from Incheon National University stepped up to the challenge and took a deep dive into the world of 5G-enabled IIoT to explore its threats and come up with a novel solution to the problem.   

“Security threats can often lead to operation or deployment failure in IIoT systems, which can create high-risk situations. So, we decided to investigate and compare available research, find out the gaps, and propose a new design for a security system that can not only detect malware attacks in IIoT systems, but also classify them,” Jeon said explaining the rationale behind the study.  

The new system created by the team utilises a method known as grayscale image visualisation with a deep learning network for monitoring the malware. It also applies a multi-level convolutional neural network (CNN) architecture to classify malware attacks into different types. They also integrated 5G into the system, which enables low latency and high throughput sharing of data and diagnostics in real time.  

The novel design demonstrated an improved accuracy that achieved 97% on the benchmark dataset, the researchers said. They discovered the reason for this accuracy is due to the system’s ability to extract complementary discriminative features by amalgamating multiple layers of information.  

“AI-based technology has dramatically changed our lives. Our system harnesses the power of AI to enable industries to recognise miscreants and prevent the entry of unreliable devices and systems in their Industrial Internet of Things networks,” Jeon summed up.