Matulytė, Raminta
Semantic integration of hybrid threat intelligence: The HiPSTer Ontological Method for cross-domain correlation in influence operationsItem type:Publication, research article[2026][S1b][S001,T007][4]; ;Paskauskas, Richard; ; Open research Europe, 2026, vol. 6, p. 1-4Hybrid threats exploit the interplay between informational, behavioural, psychological, and technical domains, making early detection challenging for security actors. While capabilities in Open-Source Intelligence (OSINT), Social Media Intelligence (SOCMINT), and Natural Language Processing (NLP) have advanced substantially, they remain siloed, leaving meaningful signals fragmented and limiting timely response to Foreign Information Manipulation and Interference (FIMI) campaigns. This paper presents the HiPSTer project’s methodological framework addressing this integration gap. The approach frames hybrid threat detection as structured sense-making rather than single-indicator classification, combining empirical use case reconstruction, comparative solution assessment, and ontological modelling. Its core is a semantic integration layer that combines Web Ontology Language (OWL) ontologies, Simple Knowledge Organisation System (SKOS) taxonomies, and Resource Description Framework (RDF) data integration, enabling systematic reconciliation of heterogeneous indicators while accommodating uncertainty. Assessment of nine existing solutions against 143 functionalities reveals that current platforms, while mature for foundational tasks, lack cross-domain semantic reasoning and dehumanisation detection capabilities that coordinated hybrid operations demand. The framework is evaluated through two complementary approaches: a case study demonstrating ontological reasoning over the escalation of demonisation in the Russia-Ukraine information environment, supported by query patterns that distinguish coordinated FIMI operations from organic discourse; and multilingual hate speech detection validation across English, Russian, Lithuanian, and Chinese benchmarks. A measurement model combining demonisation indicators with coordination co-indicators provides the logic for graduated threat assessment. The contribution is methodological. It outlines an approach through which hybrid threat analysis may balance analytical depth with operational usability, support explainability, and align with EU regulatory expectations under the AI Act, GDPR, and Law Enforcement Directive. All ontological artefacts, queries, indicator definitions, and visualisations are available publicly.
Automated regulatory compliance for AI systems in the security domain: The case of dual-use deploymentItem type:Publication, research article[2026][S1b][T007,S001,S003][40]; ;Paskauskas, Richard; ; Open research Europe., 2026, p. 1-40The 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.
12Scopus© Citations 3 Towards an optimal regulatory strategy for data protection: insights from law and economicsItem type:Publication, research article[2024][S1b][S001][19] ;Murauskas, DonatasJournal of Intellectual Property, Information Technology and E-Commerce Law (JIPITEC)., 2024, vol. 15, no. 3, p. 269-287In this paper, we examine data protection regulation from the standpoint of Law & Economics. Specifically, we analyze the advantages and disadvantages of the two distinct data protection regulation frameworks in the EU and the US. We compare these regulatory frameworks based on the criteria set by S. Shavell in his seminal work “Liability for Harm Versus Regulation of Safety”. We utilize Shavell’s model to compare the ex ante regulatory approach to data protection in the EU with the ex post liability approach of the US. This comparative analysis helps us explore whether the focus in the field of data protection should be on proactive (ex-ante) regulation or reactive (ex-post) liability. We find difficulties in comparing the regulatory frameworks, considering the dominant conceptual framework of human rights in the data protection field. However, the comparison provides valuable efficiency-based arguments on ways to optimize both regulatory frameworks.
13