(News from Nanowerk) Industrial internet of thingsor IIoT, has recently gained popularity due to its ability to create communication networks between the different components of an industry and to bring about the new revolution: Industry 4.0.
Powered by 5G wireless connectivity and artificial intelligence (IA), IIoT holds the ability to analyze critical issues and deliver solutions that can improve the operational performance of industries ranging from manufacturing to healthcare.
IoT is highly user-centric (it connects TVs, voice assistants, refrigerators, etc.), while IIoT deals with improving the health, safety or efficiency of larger systems, linking hardware to software and performing data analytics to provide real-time insights. knowledge.
However, while the IIoT has many advantages, it also comes with its share of vulnerabilities such as security threats in the form of attacks attempting to disrupt the network or siphon off resources. As the IIoT becomes more and more popular in industries, it becomes crucial to develop an effective system to handle these security issues. Thus, a team of multinational researchers led by Professor Gwanggil Jeon of the National University of Incheon took up the challenge!
They dove deep into the world of 5G-enabled IIoT to explore its threats and find a new solution to the problem. In a recent review published in IEEE Transactions on Industrial Computing (“A multi-layered deep learning approach for malware classification in 5G-enabled IIoT”), the team demonstrated an AI and deep learning based malware detection system for 5G-assisted IIoT systems.
Professor Jeon explains the rationale for the study: “Security threats can often lead to operational or deployment failure in IIoT systems, which can create high-risk situations. So we decided to investigate and compare the available research, uncover the gaps, and come up with a new design for a security system that can not only detect malware attacks in IIoT systems, but also classify them.
The system developed by the team uses a method called grayscale image visualization with a deep learning network to analyze the malware, and further applies a multi-level convolutional neural network (CNN) architecture to classify malware attack in different types. The team has also integrated this security system with 5G, which enables low latency and high-speed sharing of real-time data and diagnostics.
Compared to conventional system architectures, the new design showed improved accuracy that reached 97% on the benchmark data set. They also found that the reason for such accuracy is the system’s ability to extract complementary discriminating features by combining multiple layers of information.
This new malware classification system can be used to secure real-time connectivity applications such as smart cities and autonomous vehicles. It also provides a solid foundation for the development of advanced security systems that can curb a wide range of cybercrime activities.
“AI-based technology has dramatically changed our lives. Our system harnesses the power of AI to enable industries to recognize bad guys and prevent untrusted devices and systems from entering their IIoT networks concludes Professor Jeon.