Neural networks and AI join battle in 5G IIoT cyber attacks

A multinational team of researchers has developed a 5G-enabled deep learning approach for classifying malware attacks on the Industrial Internet of Things

The Industrial Internet of Things (IIoT) can connect entire sectors in the pursuit of an Industry 4.0 revolution, but security threats are rife, so a multinational team of researchers has developed an AI-based convolutional neural network architecture that can classify malware attacks in 5G-enabled IIoT systems.

While the traditional Internet of Things (IoT) connects TVs, voice assistants, refrigerators, and other consumer products, IIoT aims to enhance the health, safety, or efficiency of larger systems, bridging hardware with software, and carrying out data analysis to provide real-time insights.

IIoT has gained popularity due to its ability to create communication networks between different components of an industry. Powered by wireless 5G connectivity and artificial intelligence, IIoT can analyse critical problems and provide solutions to improve the operational performance of industries, including manufacturing and healthcare.

IIoT offers a wealth of advantages, but it also comes with vulnerabilities, such as security threats. In response to this challenge, a team of researchers led by Prof. Gwanggil Jeon from Incheon National University in South Korea have developed a malware detection system for 5G-assisted IIoT systems built on AI and deep learning technologies.

“Security threats can often lead to operation or deployment failure in IIoT systems, which can create high-risk situations,” says Jeon. “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.”

5G allows sharing of real-time data and diagnostics

The system developed by the team uses a method called grayscale image visualisation with a deep learning network for analysing the malware. A multi-level convolutional neural network (CNN) architecture is also used to categorise the malware attack into different types. The team also integrated this security system with 5G for sharing of real-time data and diagnostics.

The new design showed an improved accuracy that reached 97 per cent on the benchmark dataset compared to conventional system architectures. The reason behind such high accuracy is the system’s ability to extract complementary discriminative features by combining multiple layers of information, researchers discovered.

This new system can be used to secure real-time connectivity applications such as smart cities and autonomous vehicles and provides groundwork for developing advanced security systems to curb cybercrime activities. 

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

Share

Featured Articles

GPT-4 Turbo: OpenAI Enhances ChatGPT AI Model for Developers

OpenAI announces updates for its GPT-4 Turbo model to improve efficiencies for AI developers and to remain competitive in a changing business landscape

Meta Launches AI Tools to Protect Against Online Image Abuse

Tech giant Meta has unveiled a range of new AI tools to filter out unwanted images via its Instagram platform and is working to thwart threat actors

Microsoft in Japan: Investing in AI Skills to Boost Future

Tech giant Microsoft is investing US$2.9bn into AI and cloud infrastructure in Japan to upscale the country’s skills, research and cybersecurity efforts

Microsoft to Open New Hub to Advance State-of-the-Art AI

AI Strategy

SAP Continues to Develop its Enterprise AI Cloud Strategy

AI Applications

AI Consortium: Leading Tech Companies to Improve Upskilling

AI Strategy