SPINET

Development of a tool dedicated to protecting users, systems, and Internet of Things (IoT) devices based on machine learning and behavioral analysis.

The project is funded by the National Centre for Research and Development under the Cybersecurity and Digital Identity Program – CyberSecIdent.

Title: “Development of a tool dedicated to protecting users, systems, and Internet of Things (IoT) devices based on machine learning and behavioral analysis.”

The SPINET project is a joint initiative of three institutions

• Sieć Badawcza Łukasiewicz – Instytut Technik Innowacyjnych EMAG – Lider
• EFIGO Limited Liability Company (LLC).
• QED Software Limited Liability Company (LLC).

Contract number: CYBERSECIDENT/489240/IV/NCBR/2021

Project Manager from the Łukasiewicz Research Network – Institute of Innovative Technologies EMAG: Marcin Michalak
From EFIGO Spółka z ograniczoną odpowiedzialnością: Oliver Woźny
From QED Software Spółka z ograniczoną odpowiedzialnością: Antoni Jamiołkowski

PROJECT GOAL:

The goal of the project is to create a system for continuous security monitoring across a wide range of IoT devices (based on Android and Linux systems), with a particular focus on devices used for remote monitoring of gas, water, heat, and electricity networks. The solution includes a central SOC (Security Operations Center) operating in a SaaS model and dedicated monitoring software (Agent) for IoT devices. The Agent’s task is to collect and aggregate data and send it to the SOC, where security analyses are performed using machine learning algorithms. These results are then sent back to the Agent.

The SOC identifies new threats and informs the Agent, which will take protective actions, identify new threat signatures, and notify other Agents. The Agents will have the functionality to verify the system status based on existing signatures and will take action upon detecting a threat. The SOC will manage vulnerabilities by prioritizing them. Expert vulnerability assessment conducted in the SOC will enable more efficient use of information in machine learning algorithms. Experts will cyclically and incrementally evaluate both historical and incoming threats, allowing the fine-tuning of machine learning algorithms and the verification of existing threats and anomalies.

The project particularly aims to prepare the system for implementation, ready for installation and deployment on devices equipped with ARM family processors. An important aspect of the project is the development of a solution that guarantees low power consumption, ensuring applicability in devices powered by low voltage or batteries, and enabling the use of passive cooling systems.

PLANNED OUTCOMES:

• Enhancing the security of service continuity for systems using connected devices (e.g., smart metering services).
• Increased trust of end users in IoT devices.
• Increase in the number of IoT device deployments.
• Enhanced security in preventing sensitive data leaks, thereby avoiding penalties associated with such incidents.
• Increased security level in protection against “zero-day attacks.”
• Early detection of unauthorized data transmission attempts and early identification of attacks aimed at destabilizing devices and data theft.
• Reducing the risk of uncontrolled remote manipulation of IoT devices.
• Reducing the risk of IoT devices being used in botnet networks.

Dostępne dane / Available Datasets
ICPRAM2023 (https://chmura.ibemag.pl/share.cgi?ssid=0OQIat6)

Project value: PLN 5,675,433.69, including funding: PLN 5,060,266.00
Funding for Łukasiewicz – EMAG: PLN 2,029,492.00