SecurityBrief UK - Technology news for CISOs & cybersecurity decision-makers
Story image
Traditional internet security fails to meet requirements of IoT
Mon, 13th Mar 2023
FYI, this story is more than a year old

RMIT University has released guidance on how Dr. Abebe Diro's research seeks to enhance internet of things (IoT) security for space information networks.

The IoT has emerged as a rapidly growing area of technology with significant potential to transform various industries, including healthcare, transportation, manufacturing, and smart homes. However, this growth has also brought with it a host of security challenges and concerns.

Unlike traditional information technology (IT) systems, the IoT environment is challenging to secure due to resource constraints, heterogeneity, and the distributed nature of smart devices. Addressing security concerns requires a multifaceted approach that involves not only improving security standards and protocols but also implementing effective security measures at the device, network, and application levels.

Dr. Abebe Diro, Lecturer of Cyber Security at RMIT University and RMIT Centre for Cyber Security Research and Innovation (CCSRI) member, has demonstrated the failure of traditional internet security in meeting the requirements of IoT devices. Throughout his research, Diro has focused on re-thinking and re-designing the architecture and algorithms of existing security systems for IoT.

Utilising both cryptography and machine learning, Diro has successfully tested and created models with improved IoT security by decentralising aspects of the cloud and mitigating intensive computations from IoT devices. With the recent successes of deep learning in image recognition and language processing, Diro decided to apply this more layered, complex subset of machine learning to his field of study. In particular, he looked at deep learning in the context of anomaly detection systems.

Ultimately, Diro found success in traditional IT systems with reduced false alarms, but when applied to IoT, the deep learning algorithms were more prone to attack when compared with traditional, shallow machine learning models. These mixed results sent Diro deeper into anomaly detection, where he’s ventured beyond the cloud and into space.

Diro says, “There are real commonalities between IoT anomaly detection and space anomaly detection, [namely] their focus on identifying and mitigating unusual events that can have significant consequences.”

"It’s not merely the nature of each of these disciplines that align, but the physical ecosystem. Consider the miniaturisation of satellites, this increase in space hardware and activity will rely on corresponding advancements in security, just as the rapid growth of IoT has done on earth," Diro says.

Space Information Networks (SINs) are networks of space-based assets, ground stations and communication links, and detecting anomalies within these networks is challenging due to their inherent diversities. Deemed by some the new frontier of cyber security, SINs are a significant factor in national security and a major target for cyber attacks.

"By identifying anomalous yet insightful patterns in SINs, space anomaly detection is an important aspect of security protection in space. The existing methods for detecting anomaly in SINs, such as simple threshold techniques, are inaccurate, inefficient and inexplicable with high false alarm rates, high resource requirements and low scalability," Diro says.

According to a statement, Diro is now focused on building upon and applying his prior work with anomaly detection in IoT to SINs. By designing new algorithms and methods, as he’s done in the past with IoT, Diro hopes to improve the accuracy of detecting space anomalies, providing near real-time and scalable data, ultimately enhancing space security.