HET sistemų centro projektai / Projects of the HET Systems Centre

The rapid expansion of the European Union’s digital regulatory framework and recent adoption of the Artificial Intelligence Act (AI Act) has introduced complex, overlapping compliance obligations for AI systems, and consequently, their developers and users. These challenges are amplified for dual-use AI systems, which may be developed for civilian markets yet deployed in military contexts, requiring alignment with both EU regulatory instruments and defence-specific frameworks such as NATO policies. Existing approaches to regulatory compliance remain largely manual, fragmented, and difficult to scale, particularly when legal requirements must be translated into actionable, system-level specifications for dual-use contexts. This paper proposes a novel ontology-based methodology for automated regulatory compliance requirements specification for dual-use AI systems. The methodology systematically integrates legal and technical perspectives by structuring compliance obligations across deployment domains (civilian and defence), system lifecycle phases, and requirement categories, including privacy- and security-related obligations. Implemented as a machine-readable knowledge graph using RDF/Turtle, the approach enables executable compliance modelling, where regulatory obligations are formalised as machine-interpretable entities that can be queried, validated, and deployment-specifically configured through semantic reasoning and SPARQL-based analysis. The methodology is validated through a detailed case study of an AI-powered espionage detection system, demonstrating how context-aware semantic reasoning and SHACL-based validation can ensure that regulatory requirements are consistently specified and mapped to concrete system components. The proposed framework advances the state of the art by providing a rigorous, extensible foundation for compliance-by-design and automated analysis, thereby reducing compliance risk and supporting responsible AI engineering in complex omni-use regulatory environments.

Connected and Autonomous Vehicles (CAVs) are rapidly advancing toward SAE Levels 4 and 5, fundamentally reshaping human–vehicle interaction. As these systems become increasingly automated and connected, cybersecurity incidents introduce risks that extend beyond technical failure, affecting user trust, perceived safety, and acceptance. This study investigates how passengers respond when cyberattacks occur during an autonomous ride-hailing service. A driving simulator study was conducted with 50 participants, replicating a robo-taxi experience along a 5-mile urban route. Participants experienced three scenarios: a control scenario, a passive attack scenario and an active attack scenario. Following each scenario, participants evaluated their trust in the system, perceived safety, perception of risk, privacy assurance, and service intention (intention to use). The results demonstrated statistically significant differences across the three scenarios. Passive attacks were associated with reduced trust and increased uncertainty, whereas active attacks produced stronger negative responses, including higher perception of risk and lower perceived safety. Participants also expressed concern about the reliability of the automated vehicle and their personal safety when abnormal behaviour occurred. Overall, the findings underscore that cyberattacks meaningfully influence how passengers evaluate the safety, reliability, and future adoption of autonomous mobility services. These results highlight the importance of integrating human-centric impact evaluation within cybersecurity risk assessment framework and the design of secure and trustworthy autonomous transport systems.

Universities are common across all countries and perform a key function in terms of research and knowledge development as well as the development of the next generation of professionals. In this study the focus is the university sector of Australia, Lithuania and Ukraine. Each country manages their university sector differently from a security perspective. Australian universities operate under critical infrastructure regulations and foreign interference guidelines. Lithuanian institutions benefit from EU NIS2 directives and national collective defense systems. Ukrainian universities, facing intense cyber attacks since 2014 and have developed exceptional resilience through distributed infrastructure and international cooperation. This paper examines the distinct cyber security postures of the Australia, Lithuania and Ukrainian university sector.

Background: Diagnosing CNS tumors through MRI is limited by significant variability in scanner hardware, acquisition protocols, and intensity characteristics at clinical centers, resulting in substantial domain shifts that lead to diminished reliability for automated models. Methods: We present a Domain-Adaptive MRI Learning Model (DA-MLM) consisting of an adversarially aligned hybrid 3D CNN-transformer encoder with contrastive regularization and covariance-based feature harmonization. Varying sequence MRI inputs (T1, T1ce, T2, and FLAIR) were inputted to multi-scale convolutional layers followed by global self-attention to effectively capture localized tumor structure and long-range spatial context, with domain adaptation that harmonizes feature distribution across datasets. Results: On the BraTS 2020 dataset, we found DA-MLM achieved 94.8% accuracy, 93.6% macro-F1, and 96.2% AUC, improving upon previously established benchmarks by 2-4%. DA-MLM also attained Dice score segmentation of 93.1% (WT), 91.4% (TC), and 89.5% (ET), improving upon 2-3.5% for CNN and transformer methods. On the REMBRANDT dataset, DA-MLM achieved 92.3% accuracy with segmentation improvements of 3-7% over existing U-Net and expert annotations. Robustness testing indicated 40-60% less degradation under noise, contrast shift, and motion artifacts, and synthetic shifts in scanner location showed negligible performance impairment (<0.06). Cross-domain evaluation also demonstrated 5-11% less degradation than existing methods. Conclusions: In summary, DA-MLM demonstrates improved accuracy, segmentation fidelity, and robustness to perturbations, as well as strong cross-domain generalization indicating the suitability for deployment in multicenter MRI applications where variation in imaging performance is unavoidable.

Cybersecurity has become a critical challenge to policy as cyber threats continue to increase in frequency, sophistication, and societal impact, exposing the growing vulnerability of the critical infrastructure supporting vital societal functions. Globally, these risks are heightened by a persistent shortage of skilled cybersecurity professionals, which, in Europe, threatens the effective implementation of the Union’s Network and Information Security Directive 2 (NIS2) concerned with the enhancement and harmonization of the cybersecurity level across Member States, notably in terms of their critical infrastructure and involved entities. This article examines the cybersecurity skills landscape across the European Union (EU), with a specific focus on Lithuania, using the United Kingdom (UK) as a strategic benchmark subject. Adopting a comparative case study approach, the study explores and discusses governance arrangements, education and training pathways, labour-market dynamics, and quality-assurance mechanisms shaping cybersecurity workforce development. Technical, organisational, and transversal skills required to prepare an effective cybersecurity workforce in a rapidly evolving labour landscape are also discussed. Findings reveal that Lithuania faces an acute shortage of advanced practitioners and limited alignment between education provision, labour-market needs, and regulatory requirements. In response, the article proposes policy-informed strategies adapted from the UK’s structured and professionalised cybersecurity skills model, explicitly mapped to NIS2 workforce and capability requirements. Identified strategies emphasise the need of coordinated action across schools, higher education institutions, government, industry, and the wider community. Potential enablers and constraints for the operationalization of the identified strategies are further analysed and discussed. The study aims to contribute to ongoing policy debates by demonstrating how a strategic context-sensitive selection and adaptation of key components in established skills frameworks can support the development of a sustainable national cybersecurity skills ecosystem and enhance long-term digital resilience, not only in Lithuania but also in other Member States across the EU.