SHASAI, a new EU-funded project, will address cybersecurity risks in AI systems, from design to actual operation.
Funded under the Horizon Europe program, SHASAI aims to strengthen the security, resilience and reliability of AI-based systems as cybersecurity threats become more common.
Address cybersecurity risks from early design and development stages to deployment and actual operations.
Leticia Montalvillo Mendizabal, cybersecurity researcher at IKERLAN and SHASAI project coordinator, explains:
“By combining secure hardware and software, risk-driven engineering, and real-world validation, this project will help organizations deploy AI systems that are not only innovative, but also resilient, reliable, and compliant with European regulations.”
Protect AI systems from cybersecurity threats using real-world scenarios
AI systems are becoming increasingly complex, interconnected, and data-driven, making them targets of cyber-attacks and vulnerable to failures that can have real-world consequences.
This project demonstrates and validates its methods and tools in three real-world scenarios to address cybersecurity threats:
AI-enabled cutting machines in the agri-food sector Eye-tracking systems used in medical assistive technology Remotely controlled last-mile delivery vehicles in the mobility sector
These diverse use cases will allow project researchers to test their approaches in different areas while ensuring that the results are transferable to other AI applications.
The expected outcome is a robust, adaptable, and trusted security architecture that enables AI systems to remain resilient and traceable in high-risk environments and comply with evolving cybersecurity standards.
Supporting Europe’s ambition to advance trustworthy AI
SHASAI will also support Europe’s broader efforts to promote trustworthy AI by translating high-level cybersecurity and AI safety principles into concrete technical practices.
The project is aligned with key EU frameworks and initiatives such as the EU AI Act, the Cyber Resilience Act (CRA), the NIS2 Directive and the EU Cybersecurity Strategy.
The consortium combines expertise from research institutes, universities, industry and technology providers. It begins on November 1, 2025 and runs until the end of April 2029.
Source link
