Yod-Samuel Martin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yod-Samuel Martin has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jose M. Del Alamo
Universidad Politécnica de Madrid
2 shared publications - Juan C. Yelmo
Information Processing and Telecommunications Center, ETSI Telecomunicacin, Universidad Politcnica de Madrid, Madrid, Spain
2 shared publications - Julio César Caiza Ñacato
Department of Electronics, Telecommunications and Information Networks, National Polytechnic School, Quito 170525, Ecuador
2 shared publications - Alejandra Ruiz
Tecnalia
1 shared publication - Amelie Gyrard
Trialog, Paris, France
1 shared publication - Danny S. Guaman
Departamento de Electrónica, Telecomunicaciones y Redes de Información, Facultad de Ingeniería Eléctrica y Electrónica, Escuela Politécnica Nacional, Quito 170525, Ecuador
1 shared publication
Latest Publications
- Open Access
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 19579-19606
Experimental Evaluation of AI-Augmented Cybersecurity Requirements Generation Leveraging LLMs’ Capabilities
When it comes to cybersecurity requirements, catalogs of standard controls are a double-edged sword: they offer reusable resources applicable anywhere, yet they entail tedious, error-prone manual instantiation work. As the definitions of these cybersecurity controls are written in natural language, we analyze whether large language models (LLMs) may help automate that process. We ran an empirical evaluation where frontier versions of LLaMa, Qwen, Mixtral, and GPT were asked, leveraging best prompting practice, to generate cybersecurity requirements for a realistic system, departing from its functional specification plus definitions of abstract cybersecurity controls extracted from ISO/IEC 27002. We compared the results to a ground truth created by human experts, and a gold standard pooled from the aggregation of all human- and LLM-produced results, considering phenomena such as hallucinations, new requirements discovered by LLMs, or partial overlaps. Results show that open-weights LLMs can parallel human experts in coverage and help uncover additional requirements when used under human-in-the-loop curation. Relative F2 score against the gold standard (prioritizing recall over precision) reached 1.14× in the best LLM configuration (in comparison to human experts): a LLaMa 3.1 405B model, prompted with an explicit chain-of-thought pipeline made of three sequential steps and four parallel and coalesced runs, and moderate values for hyperparameters that balance diversity and determinism. Our work contributes a benchmark of applied capabilities of LLMs for security by design in non-code artifacts. Although recall values leave room for improvement as LLMs advance, results provide initial evidence that this approach is feasible in our case study.
- 28 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 19579-19606
Open AccessExperimental Evaluation of AI-Augmented Cybersecurity Requirements Generation Leveraging LLMs’ Capabilities
When it comes to cybersecurity requirements, catalogs of standard controls are a double-edged sword: they offer reusable resources applicable anywhere, yet they entail tedious, error-prone manual instantiation work. As the definitions of these cybersecurity controls are written in natural language, we analyze whether large language models (LLMs) may help automate that process. We ran an empirical evaluation where frontier versions of LLaMa, Qwen, Mixtral, and GPT were asked, leveraging best prompting practice, to generate cybersecurity requirements for a realistic system, departing from its functional specification plus definitions of abstract cybersecurity controls extracted from ISO/IEC 27002. We compared the results to a ground truth created by human experts, and a gold standard pooled from the aggregation of all human- and LLM-produced results, considering phenomena such as hallucinations, new requirements discovered by LLMs, or partial overlaps. Results show that open-weights LLMs can parallel human experts in coverage and help uncover additional requirements when used under human-in-the-loop curation. Relative F2 score against the gold standard (prioritizing recall over precision) reached 1.14× in the best LLM configuration (in comparison to human experts): a LLaMa 3.1 405B model, prompted with an explicit chain-of-thought pipeline made of three sequential steps and four parallel and coalesced runs, and moderate values for hyperparameters that balance diversity and determinism. Our work contributes a benchmark of applied capabilities of LLMs for security by design in non-code artifacts. Although recall values leave room for improvement as LLMs advance, results provide initial evidence that this approach is feasible in our case study.
- Open Access
- 7 November 2022
- Published by Springer Nature in Software and Systems Modeling
- Vol. 22 (4) , 1175-1196
Modeling ecosystems of reference frameworks for assurance: a case on privacy impact assessment regulation and guidelines
To assure certain critical quality properties (e.g., safety, security, or privacy), supervisory authorities and industrial associations provide reference frameworks such as standards or guidelines that in some cases are enforced (e.g., regulations). Given the pace at which both technical advancements and risks appear, there is an increase in the number of reference frameworks. As several frameworks might apply for same systems, certain overlaps appear (e.g., regulations for different countries where the system will operate, or generic standards in conjunction with more concrete standards for a given industrial sector or system type). We propose the use of modelling for alleviating the complexity of these reference frameworks ecosystems, and we provide a tool-supported method to create them for the benefit of different stakeholders. The case study is based on privacy data protection, and more concretely on privacy impact assessment processes. The European GDPR regulates the movement and processing of personal data, and, contrary to available software engineering privacy guidelines, articles in legal texts are usually difficult to translate to the underlying processes, artefacts and roles that they refer to. To facilitate the mutual comprehension of legal experts and engineers, in this work we investigate how mappings can be created between these two domains of expertise. Notably, we rely on modelling as a central point. We modelled the legal requirements of the GDPR on data protection impact assessments, and then, we selected the ISO/IEC 29134, a mainstream engineering guideline for privacy impact assessment, and, taking a concrete sector as example, the EU Smart Grid Data Protection Impact Assessment template. The OpenCert tool was used for providing technical support to both the modelling and the creation of the mapping models in a systematic way. We provide a qualitative evaluation from legal experts and privacy engineering practitioners to report on the benefits and limitations of this approach.
- 7 November 2022
- Published by Springer Nature in Software and Systems Modeling
- Vol. 22 (4) , 1175-1196
Open AccessModeling ecosystems of reference frameworks for assurance: a case on privacy impact assessment regulation and guidelines
To assure certain critical quality properties (e.g., safety, security, or privacy), supervisory authorities and industrial associations provide reference frameworks such as standards or guidelines that in some cases are enforced (e.g., regulations). Given the pace at which both technical advancements and risks appear, there is an increase in the number of reference frameworks. As several frameworks might apply for same systems, certain overlaps appear (e.g., regulations for different countries where the system will operate, or generic standards in conjunction with more concrete standards for a given industrial sector or system type). We propose the use of modelling for alleviating the complexity of these reference frameworks ecosystems, and we provide a tool-supported method to create them for the benefit of different stakeholders. The case study is based on privacy data protection, and more concretely on privacy impact assessment processes. The European GDPR regulates the movement and processing of personal data, and, contrary to available software engineering privacy guidelines, articles in legal texts are usually difficult to translate to the underlying processes, artefacts and roles that they refer to. To facilitate the mutual comprehension of legal experts and engineers, in this work we investigate how mappings can be created between these two domains of expertise. Notably, we rely on modelling as a central point. We modelled the legal requirements of the GDPR on data protection impact assessments, and then, we selected the ISO/IEC 29134, a mainstream engineering guideline for privacy impact assessment, and, taking a concrete sector as example, the EU Smart Grid Data Protection Impact Assessment template. The OpenCert tool was used for providing technical support to both the modelling and the creation of the mapping models in a systematic way. We provide a qualitative evaluation from legal experts and privacy engineering practitioners to report on the benefits and limitations of this approach.
- Open Access
- 20 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 66512-66535
Reusable Elements for the Systematic Design of Privacy-Friendly Information Systems: A Mapping Study
Privacy by design is a new paradigm that promotes embedding privacy considerations throughout the development of information systems, to protect user privacy. Privacy engineering is the nascent field of research and practice that aims to realize this new paradigm systematically and efficiently, by delivering reusable elements such as methods, techniques, and tools that software and systems engineers can apply in their daily work. However, as a new field, its contributions are still scattered, and there is little information on their quantity or maturity. To bridge this gap, we have carried out a systematic mapping study to provide engineers and researchers with a snapshot of the reusable elements available for the systematic design of privacy-friendly software-based information systems. The results show that there is an emerging and growing interest in the field, being privacy patterns, the hottest research topic. However, the maturity of some of the contributions found is still low as they usually lack empirical evidence that demonstrates their benefits, which may hinder their adoption in practice. In this paper, we describe the most advanced research areas and discuss some of the gaps found, suggesting areas where researchers and funding institutions can focus their efforts.
- 20 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 66512-66535
Open AccessReusable Elements for the Systematic Design of Privacy-Friendly Information Systems: A Mapping Study
Privacy by design is a new paradigm that promotes embedding privacy considerations throughout the development of information systems, to protect user privacy. Privacy engineering is the nascent field of research and practice that aims to realize this new paradigm systematically and efficiently, by delivering reusable elements such as methods, techniques, and tools that software and systems engineers can apply in their daily work. However, as a new field, its contributions are still scattered, and there is little information on their quantity or maturity. To bridge this gap, we have carried out a systematic mapping study to provide engineers and researchers with a snapshot of the reusable elements available for the systematic design of privacy-friendly software-based information systems. The results show that there is an emerging and growing interest in the field, being privacy patterns, the hottest research topic. However, the maturity of some of the contributions found is still low as they usually lack empirical evidence that demonstrates their benefits, which may hinder their adoption in practice. In this paper, we describe the most advanced research areas and discuss some of the gaps found, suggesting areas where researchers and funding institutions can focus their efforts.
- 9 June 2018
- Published by Springer Nature
- p. 15-24
Towards Organizing the Growing Knowledge on Privacy Engineering
- 9 June 2018
- Published by Springer Nature
- p. 15-24
Towards Organizing the Growing Knowledge on Privacy Engineering