AI Protects 5G-enabled IIoT Systems from Malware

IoT is known by many today who live in a smart home – TVs, refrigerators, door locks and even light bulbs are connected by IoT. Industrial IoT works in similar ways, but is utilized more in the manufacturing and healthcare industries to drive automation and process efficiency. So, naturally it takes IoT a step further as it connects larger machines and devices to collect, monitor and analyze massive volumes of data to improve operational and business performance.

As the world entered Industry 4.0, the age of IIoT, 5G was thought to be the ideal way to create communication networks between different components of an industry. It may well be. However, not everything was perfect.

Bad actors attempted to disturb the network by exposing IIoT vulnerabilities. With multiple devices on a network, it takes only one device to abuse that network. A solution needed to be innovated to handle the security risks of IIoT.

To take on that challenge, a team of multinational researchers led by Professor Gwanggil Jeon from Incheon National University in South Korea explored the threats of 5G-enabled IIoT and presented an AI- and deep learning-based malware detection system for 5G-assisted IIoT systems.

Jeon said that the team wanted to investigate available research for comparison, which was used to find out the gaps and propose a new design for a security system that will detect and classify malware attacks in IIoT systems.

The system uses a method called grayscale image visualization with a deep learning network for analyzing malware. The system then applied a multi-level convolutional neural network architecture to categorize the malware attack into different types. The team also integrated this security system with 5G, which allows for low latency and high throughput sharing of real-time data and diagnostics.

The new design shows improved accuracy that reached 97% in benchamark testing. The team further discovered that the high accuracy was due to the system’s ability to extract complementary discriminative features by combining multiple layers of information.

“AI-based technology has dramatically changed our lives,” said Jeon. “Our system harnesses the power of AI to enable industries to recognize miscreants and prevent the entry of unreliable devices and systems in their IIoT networks.”

The research team revealed that the new malware classification system is also beneficial to secure real-time connectivity applications such as smart cities and autonomous vehicles and provides a solid foundation for advanced security systems curb cybercrime activities.