Applying AI to Industrial Cybersecurity: Radiflow and Fraunhofer to Partner

February 13, 2020 by Alessandro Mascellino

The collaboration will focus on applying advanced AI and machine learning to automatically detect non-compliant behaviors in machinery used in industrial automation networks.

Cybersecurity provider Radiflow and the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (Fraunhofer IOSB) have just announced a new joint research project.

In order to achieve this goal, Radiflow and the Fraunhofer IOSB will evaluate graph-based and semantic approaches for event correlation and context awareness.


Researchers in the lab at Fraunhofer

Researchers at Fraunhofer working in the cybersecurity lab. Image used courtesy of Fraunhofer. 


Autonomous Industrial Cybersecurity Assistance System

According to a press release on the Radiflow website, the results of the research will go towards the development of an Autonomous Industrial Cybersecurity Assistance System (AICAS) prototype.

The new self-learning system will be designed to understand the underlying behaviors of industrial automation networks and the different roles of connected assets.

This will allow the AICAS prototype to build on existing approaches for detecting anomalies and deviations as well as dynamically detect new and unknown cyber threats.

“Determining if abnormal behavior has been caused by normal operational activities or by cyber-attackers is critical for understanding and securing an operational technology (OT) network,” said Yehonatan Kfir, CTO of Radiflow, commenting on the news.

Kfir explained how AI has the potential to improve the situational awareness of OT networks by distinguishing between abnormal behavior caused by regular operations and abnormal behavior that is connected to cyberattack interferences.

The hope is that, in time, the AICAS prototype will develop itself enough to create new measuring standards to monitor behavior on OT networks on a larger scale.


Mobile Cybersecurity demonstrator

A look at Fraunhofer's mobile cybersecurity demonstrator in their research lab. Image used courtesy of Fraunhofer. 


A Fruitful Partnership

Fraunfoer is a non-profit organization that focuses on the research of direct utility to private and public enterprise. The non-profit partners with companies all over the world to aid in research for products and applications. 

The Fraunhofer Institute of Optronics, System Technologies, and Image Exploitation is a research facility focusing on Smart Production, information management, and multi-sensor systems. The institute, however, is a part of a larger academic network: The Fraunhofer Society.

The Society is a research institution based in Dresden, Germany, and comprises 72 institutes spread throughout the country. Each of the institutes focuses on a different field of applied science, and many of them are well-known for developing innovative technical solutions.

For example, in November last year, the Fraunhofer Institute for Photonic Microsystems introduced a new optical and wireless time-sensitive networking solution that is both optical and wireless. Radiflow, on the other hand, is a company developing industrial cybersecurity products for critical business operations.

The company offers several solutions for ICS/SCADA networks, designed for users to maintain visibility and control of their OT networks. 


Intelligent Threat Detection Tools

Radiflow also provides Secure Gateway tools and an Intelligent Threat Detection tool called iSID that is somehow a precursor to the new AICA prototype.

In fact, at the center of the collaboration between Radiflow and Fraunhofer IOSB is the agreement that the former will incorporate the new capabilities of the AICAS prototype into iSID.


iSID from Radiflow.

iSID Intelligent Threat Detection tool displayed on a computer screen. Image used courtesy of Radiflow. 


“We are excited to partner with Fraunhofer IOSB on this innovative research project,” Kfir said.

“We expect that the outcome of this research will expand the cyber-monitoring capacities for our customers and MSSP partners with new capabilities that require less analyst input to highlight the most critical events on dynamically changing OT networks,” he concluded.


The project is expected to last two years and will be financed by the Innovation Authority in Israel and the Federal Ministry of Education and Research in Germany.


What kind of innovative research do you see coming out of this partnership?