Connect with us

Inovation

Defending the Future: Safeguarding AI Systems with SHASAI Cybersecurity Protection

Published

on

SHASAI project to protect AI systems against cybersecurity threats

Addressing Cybersecurity Risks in AI Systems: The SHASAI Project

SHASAI, a new EU-funded initiative, is set to tackle cybersecurity risks in AI systems from inception to real-world application. Supported by the Horizon Europe programme, SHASAI aims to enhance the security, resilience, and trustworthiness of AI-based systems amidst escalating cybersecurity threats.

From the initial design phase to deployment and operational stages, SHASAI will confront cybersecurity risks comprehensively. Leticia Montalvillo Mendizabal, Cybersecurity Researcher at IKERLAN and SHASAI Project Coordinator, emphasized the project’s ambition to address AI cybersecurity as a lifecycle challenge, integrating secure hardware and software, risk-driven engineering, and real-world validation.

Employing Real-World Scenarios for Cybersecurity Protection

As AI systems grow in complexity and connectivity, they become prime targets for cyber-attacks and susceptible to critical failures with tangible consequences. SHASAI will validate its methodologies in three real-world scenarios:

  • AI-enabled cutting machines in the agrifood sector
  • Eye-tracking systems in assistive healthcare technologies
  • Tele-operated last-mile delivery vehicle in the mobility sector

By testing diverse use cases, SHASAI aims to ensure the transferability of its results across various AI applications, culminating in a robust security architecture that upholds resilience, traceability, and compliance with evolving cybersecurity standards.

Promoting Trustworthy AI in Europe

SHASAI translates high-level cybersecurity and AI safety principles into practical technical measures, aligning with key EU frameworks such as the EU AI Act, Cyber Resilience Act (CRA), NIS2 Directive, and EU Cybersecurity Strategy. The project consortium, comprising research institutions, universities, industry partners, and technology providers, commenced operations on November 1, 2025, with a scheduled completion date in April 2029.

See also  Revolutionizing Flood Alert Systems in Data-Scarce Regions with AI Technology

Trending