1. Towards a sustainable cybersecurity governance : threat modelling with large language modelsNika Jeršič, Muhamed Turkanović, Tina Beranič, 2025, original scientific article Abstract: With the increased complexity of applications and systems, threat modelling struggles to keep pace with the evolution of risks. This article addresses this challenge by exploring how large language models (LLMs) can be leveraged to create comprehensive threat models across different risk assessment methodologies. We examine whether a single generic prompt can support frameworks such as LINDDUN, PASTA, and STRIDE, despite their different requirements. Through this comparative analysis, we identify components that enable AI-based assessments, while acknowledging that privacy, regulatory, and dynamic risks require adaptation of the frameworks. Our findings show that a universal guideline is feasible for broad applications, but adaptation is necessary for effective use. Overall, LLM-based threat modelling improves the accessibility, repeatability, and effectiveness of risk analysis and supports stronger and more sustainable practices.
Keywords: cybersecurity, large language models, threat modelling, sustainability, resilient infrastructure, SDG 9
Published in DKUM: 02.12.2025; Views: 0; Downloads: 2
 Full text (875,62 KB) |
2. Large language models for G-code generation in CNC machining: A comparison of ChatGPT-3.5 and ChatGPT-4oKristijan Šket, David Potočnik, Miran Brezočnik, Mirko Ficko, Simon Klančnik, 2025, original scientific article Abstract: This research explores the viability of producing ISO G-code for 3-axis machining with OpenAI's Chat Generative Pre-Trained Transformer models, particularly ChatGPT-3.5 and the newer GPT-4o. G-code (RS-274-D, ISO 6983) converts human directives into commands that machines can understand, controlling toolpaths, spindle velocities, and feed rates to produce particular aspects of an object. Previously, G-code was generated either by hand or through the use of computer-aided manufacturing (CAM) software along with machine-specific post-processors, both of which may require considerable time and expense. This research aimed to assess the practicality and effectiveness of specific large language models (LLMs) in generating G-code. The assessment took place in three distinct phases on a sample component that required 3-axis machining. These phases included: (1) the self-generated production of G-code for the sample component, (2) the examination of the independently generated G-code in the CAM application, and (3) the recognition and justification of mistakes in the G-code. The outcomes indicated varying abilities with promising findings. This method could accelerate and possibly enhance manufacturing workflows by decreasing reliance on expensive CAM software and specialized knowledge.
Keywords: generative artificial intelligence, intelligent manufacturing, large language models (LLM), ChatGPT, CNC machining, G-code programming
Published in DKUM: 28.11.2025; Views: 0; Downloads: 7
Full text (4,02 MB)
This document has many files! More... |
3. Method guide for the inclusion of travel writing into communication skills curriculaMojca Kompara Lukančič, Jasna Potočnik Topler, 2024, independent scientific component part or a chapter in a monograph Abstract: In the following chapter we outline the preparation of a method guide for the inclusion of travel writing into communication skills curricula. In the introduction we present an overview of travel writing where we also discuss the basic concepts of communication skills. Furter, we expand the theory of readings and examples of good practice in relation to topics of travel writing and link it to the concept of green curricula for a sustainable future. The paper further presents an analysis of communication skills curricula in travel writing from several higher education institutions. The analysis functions as an example of good practice in the preparation of a common methodology for the inclusion of travel writing into communication skills curricula and the preparation of tasks for undergraduate and master level of education; these are also presented in the chapter.
Keywords: method guide, travel writing, travelers' writings, communication skills, educational programs, didactics, curricula, language
Published in DKUM: 17.11.2025; Views: 0; Downloads: 0
Full text (394,48 KB)
This document has many files! More... |
4. Human-led and artificial intelligence-automated critical appraisal of systematic reviews : comparative evaluationLucija Gosak, Gregor Štiglic, Wilson Tam, Dominika Vrbnjak, 2025, original scientific article Abstract: Aim To evaluate and compare human-led and artificial intelligence-automated critical appraisal of evidence. Background Critical appraisal is essential in evidence-based practice, yet many nurses lack the skills to perform it. Large language models offer potential support, but their role in critical appraisal remains underexplored. Design We conducted a comparative study to evaluate the performance of five commonly used large language models versus two human reviewers in appraising four systematic reviews on interventions to reduce medication administration errors. Methods We compared large language models and two human reviewers in independently appraising four systematic reviews using the JBI Critical Appraisal Checklist. These models were Perplexity Sonar (Pro), Claude 3.7 Sonnet, Gemini 2.0 Flash, GPT-4.5 and Grok-2. All models received identical full texts and standardized prompts. Responses were analyzed descriptively and agreement was assessed using Cohen’s Kappa. Results Large language models showed full agreement with human reviewers on five of 11 JBI items. Most disagreements occurred in appraising search strategy, inclusion criteria and publication bias. The agreement between human reviewers and large language models ranged from slight to moderate. The highest level of agreement was observed with Claude (κ = 0.732), while the lowest level was observed with Gemini (κ = 0.394). Conclusion Large language models can support aspects of critical appraisal evidence but lack contextual reasoning and methodological insight required for complex judgments. While Claude 3.7 Sonnet aligned most closely with human reviewers, human oversight remains essential. Large language models should serve as adjuncts and not substitutes for evidence-based practice.
Keywords: artificial intelligence in healthcare, multimodal large language models, nursing, evidence-based practice
Published in DKUM: 12.11.2025; Views: 0; Downloads: 1
 Link to file |
5. From zero to one: a new perspective on the fuzzy front end of innovation and the Stage-Gate® modelPeter Alešnik, Igor Vrečko, Iztok Palčič, 2025, original scientific article Abstract: The Stage-Gate® model has historically provided a systematic framework for New Product Development (NPD). However, the evolving landscape of innovation necessitates continuous enhancement. This paper redefines the model's foundational structure by advocating for the recognition of the Discovery Phase as Stage 1, emphasizing its essential role in aligning initial ideation with strategic goals, streamlining processes, and enhancing NPD efforts. Using a mixed-methods approach, including a systematic literature review, synthesis of illustrative examples and secondary data and case study analysis, the research demonstrates that formalizing the Discovery Phase improves earlystage decision-making, enhances alignment between front-end exploration and downstream execution and mitigates risks by supporting more informed project development. Synthesised sectoral examples show that incorporating the Discovery Phase improves feasibility, reduces risk, and boosts efficiency. For example, simulation planning early in innovation process increased manufacturing throughput by 52 %, while early IP checks lowered infringement risk. The proposed revision boosts the Stage-Gate® model's adaptability and integration with modern methodologies such as AI, Agile, Lean Startup, Design Thinking and TRIZ. The findings highlight how this change promotes a comprehensive approach to NPD. The implications extend to practical applications and future research, offering organizations a flexible framework that meets modern market and technological demands.
Keywords: Stage-Gate® model, fuzzy front end of innovation (FFEI), new product development (NPD), innovation management, discovery phase, agile, TRIZ, design thinking, large language model (LLM), sustainability
Published in DKUM: 03.11.2025; Views: 0; Downloads: 5
Full text (641,93 KB)
This document has many files! More... |
6. Detection of malicious software using large language modelsMartina Tivadar, 2025, master's thesis Abstract: This thesis examines the success rate of large language models (LLM) in detecting macOS malware through Endpoint Security logs. A literature review and 144 experiments with three ChatGPT variants and six prompt types evaluated accuracy, precision, recall, specificity, and F1-score. Results show that prompt wording is crucial: zero-shot and chain-of-thought prompts performed best, while conservative prompts minimized false positives but missed threats. GPT-4o and o1 outperformed o4-mini but showed similar results. Findings suggest LLMs can support, but not replace, traditional detection, with prompt design proving as important as model choice.
Keywords: malware, large language models, detection
Published in DKUM: 03.11.2025; Views: 0; Downloads: 6
Full text (29,72 MB) |
7. English Phonetic Transcription in Slovene Secondary Schools : master's thesisUrška Kajbič, 2025, master's thesis Abstract: This thesis explores the role of phonetic transcription in teaching English pronunciation to Slovene secondary school students. Pronunciation has long been marginalised in EFL classrooms, yet it is crucial for intelligibility. For Slovene learners, whose L1 is syllable-timed, the main difficulty lies in adapting to the stress-timed rhythm of English, especially in recognising word stress.
The research combined two parts: an analysis of six secondary school coursebooks and an experimental study. The coursebook analysis revealed that phonetic transcription is often limited to glossaries, leaving learners without clear guidance on stress placement. The experiment compared traditional teaching with a kinaesthetic technique—clapping for syllables. Results showed that the experimental group did not outperform the control group in transcribing -ed endings or schwa. However, this outcome points to a transitional stage: the experimental group had already disrupted Slovene stress patterns but had not yet stabilised English ones.
The findings highlight the importance of phonetic transcription as a tool that bridges segmental and suprasegmental levels, supports the shift from orthography to pronunciation, and makes hidden features such as vowel reduction and allomorphic variation visible. Combined with kinaesthetic techniques, it offers a pathway for more systematic and effective pronunciation teaching in Slovene classrooms.
Keywords: phonetic transcription, language learning, pronunciation teaching, word stress, syllable clapping
Published in DKUM: 16.10.2025; Views: 0; Downloads: 11
Full text (5,54 MB) |
8. |
9. From zero to one: a new perspective on the fuzzy front end of innovation and the Stage-Gate® modelPeter Alešnik, Igor Vrečko, Iztok Palčič, 2025, original scientific article Abstract: The Stage-Gate® model has historically provided a systematic framework for New Product Development (NPD). However, the evolving landscape of innovation necessitates continuous enhancement. This paper redefines the model's foundational structure by advocating for the recognition of the Discovery Phase as Stage 1, emphasizing its essential role in aligning initial ideation with strategic goals, streamlining processes, and enhancing NPD efforts. Using a mixed-methods approach, including a systematic literature review, synthesis of illustrative examples and secondary data and case study analysis, the research demonstrates that formalizing the Discovery Phase improves earlystage decision-making, enhances alignment between front-end exploration and downstream execution and mitigates risks by supporting more informed project development. Synthesised sectoral examples show that incorporating the Discovery Phase improves feasibility, reduces risk, and boosts efficiency. For example, simulation planning early in innovation process increased manufacturing throughput by 52 %, while early IP checks lowered infringement risk. The proposed revision boosts the Stage-Gate® model's adaptability and integration with modern methodologies such as AI, Agile, Lean Startup, Design Thinking and TRIZ. The findings highlight how this change promotes a comprehensive approach to NPD. The implications extend to practical applications and future research, offering organizations a flexible framework that meets modern market and technological demands.
Keywords: Stage-Gate® model, fuzzy front end of innovation (FFEI), new product development (NPD), innovation management, discovery phase, agile, TRIZ, design thinking, large language model (LLM), sustainability
Published in DKUM: 13.10.2025; Views: 0; Downloads: 6
Full text (641,93 KB) |
10. From model to mechanism : enforcing delegated authority in ssi with language-based securityMuhamed Turkanović, Vid Keršič, Alen Horvat, Dominik Beron, Špela Čučko, 2025, original scientific article Abstract: Delegation of authority remains a critical yet insufficiently addressed capability in SelfSovereign Identity (SSI) systems. Building on an existing delegation model that introduced the concept of a Verifiable Mandate (VM) for expressing authority and access rights, this paper extends the approach with a rigorous formalization of delegation semantics, enabling unambiguous reasoning over roles, grants, and constraints. The formal model is aligned with standards from the World Wide Web Consortium (W3C), and its constructs are embedded into an extended credential schema that preserves compatibility with the Verifiable Credentials (VC) data model while introducing delegation-specific attributes. A generalized VM schema is defined, supporting both generic and business-specific instantiations, and ensuring structural and semantic interoperability. Policy compliance is operationalized through a policy-based enforcement architecture, where rules are authored in the Rego language and evaluated at runtime by the Open Policy Agent (OPA). The architecture incorporates trusted registries for schema and policy distribution, allowing verifiers to define and enforce context-specific delegation rules in a modular and interoperable manner. Validation through realistic scenarios, such as postal service and academic use cases, demonstrates how formal semantics, schema validation, and language-based policy enforcement can be combined to enable secure, verifiable, and context-aware delegation in SSI ecosystems.
Keywords: self-sovereign identity, delegation, verifiable mandate, formalization, policy-based enforcement, verifiable credentials, blockchain, language-based security
Published in DKUM: 02.10.2025; Views: 0; Downloads: 9
Full text (1,46 MB) |
