Catalina Mihaela Priescu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Catalina Mihaela Priescu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Daniela Joita
Department of Informatics, Faculty of Informatics, Titu Maiorescu University, 040051 Bucharest, Romania
3 shared publications - Iustin Priescu
Department of Informatics, Faculty of Informatics, Titu Maiorescu University, 040051 Bucharest, Romania
3 shared publications - Mihai Alexandru Botezatu
Department of Informatics, Statistics and Mathematics, School of Computer Science for Business Management, Romanian American University, 012101 Bucharest, Romania
2 shared publications - Mironela Pirnau
Department of Informatics, Faculty of Informatics, Titu Maiorescu University, 040051 Bucharest, Romania
2 shared publications - Geanina Silviana Banu
Department of Informatics, Faculty of Informatics, Titu Maiorescu University, 040051 Bucharest, Romania
1 shared publication - Ionica Oncioiu
Faculty of Economics and Business Administration, “Eugeniu Carada” Doctoral School of Economic Sciences, University of Craiova, 200585 Craiova, Romania
1 shared publication
Latest Publications
- Open Access
- 18 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (8) , 1724
From Vector Space to Symbolic Space: Informational and Semantic Analysis of Benign and DDoS IoT Traffic Using LLMs
This paper investigates the feasibility of using Large Language Models (LLMs) for the structural analysis of flow-based network data. This analysis is carried out in the presence of a structural difference between the multidimensional numerical space of IoT features and the symbolic space in which LLMs operate. The primary objective was the development of a formal framework that enables the controlled transformation of numerical data into linguistically analyzable semantic representations, without resorting to classification or machine learning mechanisms. We propose the Semantic Flow Encoding (SFE) mechanism, a deterministic method for robust discretization and behavioral abstraction that converts the numerical characteristics of Internet of Things (IoT) flows into structural semantic descriptions using the Canadian Institute for Cybersecurity Internet of Things Device Identification and Anomaly Detection (CIC IoT-DIAD) 2024 dataset. Through formal informational measures, it is demonstrated that the existence of an intrinsic structural difference between benign and DDoS traffic in the analyzed dataset. In the validation stage, we evaluated whether these informational differences are reflected at the level of linguistic abstraction through controlled inference experiments in IBM WatsonX. The present paper suggests that LLMs may support semantic auditing of distributional structure when guided by a formal encoding layer. In this manner, a reproducible framework for integrating numerical security data into language-model-based analysis is suggested.
- 18 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (8) , 1724
Open AccessFrom Vector Space to Symbolic Space: Informational and Semantic Analysis of Benign and DDoS IoT Traffic Using LLMs
This paper investigates the feasibility of using Large Language Models (LLMs) for the structural analysis of flow-based network data. This analysis is carried out in the presence of a structural difference between the multidimensional numerical space of IoT features and the symbolic space in which LLMs operate. The primary objective was the development of a formal framework that enables the controlled transformation of numerical data into linguistically analyzable semantic representations, without resorting to classification or machine learning mechanisms. We propose the Semantic Flow Encoding (SFE) mechanism, a deterministic method for robust discretization and behavioral abstraction that converts the numerical characteristics of Internet of Things (IoT) flows into structural semantic descriptions using the Canadian Institute for Cybersecurity Internet of Things Device Identification and Anomaly Detection (CIC IoT-DIAD) 2024 dataset. Through formal informational measures, it is demonstrated that the existence of an intrinsic structural difference between benign and DDoS traffic in the analyzed dataset. In the validation stage, we evaluated whether these informational differences are reflected at the level of linguistic abstraction through controlled inference experiments in IBM WatsonX. The present paper suggests that LLMs may support semantic auditing of distributional structure when guided by a formal encoding layer. In this manner, a reproducible framework for integrating numerical security data into language-model-based analysis is suggested.
- Open Access
- 16 March 2026
- Published by MDPI AG in Preprints.org
From Vector Space to Symbolic Space: Informational and Semantic Analysis of Benign and DDoS IoT Traffic Using LLMs
In this paper, we investigate the feasibility of using Large Language Models (LLMs) for the structural analysis of flow-based network data, considering the fundamental onto-logical difference between the multidimensional numerical space of IoT data and the symbolic space in which these models operate. The primary objective was the development of a formal framework that enables the controlled transformation of numerical data into linguistically analyzable semantic representations, without resorting to classification or machine-learning mechanisms. We propose the SFE mechanism, a deterministic method for robust discretization and behavioral abstraction that converts the numerical characteristics of IoT flows into structural semantic descriptions, based on the CIC IoT-DIAD 2024 [1] dataset. Through formal informational measures, we demonstrate the existence of an intrinsic structural difference between benign and DDoS traffic in the analyzed dataset. In the validation stage, we evaluated whether these informational differences are reflected at the level of linguistic abstraction through controlled inference experiments in IBM WatsonX [2]. The paper demonstrates that LLMs can work as mechanisms for semantic auditing of distributional structure when supported by a formal encoding layer, offering a reproducible framework for integrating numerical security data into language-model-based analysis.
- 16 March 2026
- Published by MDPI AG in Preprints.org
Open AccessFrom Vector Space to Symbolic Space: Informational and Semantic Analysis of Benign and DDoS IoT Traffic Using LLMs
In this paper, we investigate the feasibility of using Large Language Models (LLMs) for the structural analysis of flow-based network data, considering the fundamental onto-logical difference between the multidimensional numerical space of IoT data and the symbolic space in which these models operate. The primary objective was the development of a formal framework that enables the controlled transformation of numerical data into linguistically analyzable semantic representations, without resorting to classification or machine-learning mechanisms. We propose the SFE mechanism, a deterministic method for robust discretization and behavioral abstraction that converts the numerical characteristics of IoT flows into structural semantic descriptions, based on the CIC IoT-DIAD 2024 [1] dataset. Through formal informational measures, we demonstrate the existence of an intrinsic structural difference between benign and DDoS traffic in the analyzed dataset. In the validation stage, we evaluated whether these informational differences are reflected at the level of linguistic abstraction through controlled inference experiments in IBM WatsonX [2]. The paper demonstrates that LLMs can work as mechanisms for semantic auditing of distributional structure when supported by a formal encoding layer, offering a reproducible framework for integrating numerical security data into language-model-based analysis.
- Open Access
- 13 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1206
BCI-Inspired Adaptive Agents in Human–Robot Interaction: A Structural Framework for Coordinated Interaction Design
The accelerated integration of intelligent agents in user-centered digital environments has intensified research in the field of Human–Robot Interaction, especially regarding mechanisms for adaptive, intuitive, and cognitively aligned communication. The present study develops and empirically examines a structural model of BCI-inspired adaptive agents designed to support coordinated interaction in HRI contexts. The study analyzes users’ perceptions of standardized hypothetical interaction scenarios involving BCI-inspired adaptive digital agents, where BCI inspiration is conceptual and refers to adaptive architectures interpreting behavioral cues rather than direct neural signal acquisition. The proposed model integrates four main constructs—perceived technological innovation, user involvement, agent adaptivity, and digital synergy—and examines their associations with user satisfaction in digital collaborative environments. Data were collected through an anonymous questionnaire (N = 268) and analyzed using structural equation modeling with the PLS-SEM method. The structural model demonstrates substantial explanatory power, accounting for 66.8% of the variance in user satisfaction (R2 = 0.668). The study contributes by empirically supporting a scenario-based structural evaluation framework suitable for early-stage adaptive HRI system design. The results highlight the role of digital synergy in aligning innovation, engagement, and adaptive behavior in BCI-inspired adaptive HRI systems, providing directions for the design of adaptive robotic agents oriented toward coordinated interaction, user-centered integration, and responsible use in collaborative digital ecosystems.
- 13 March 2026
- Published by MDPI AG in Electronics
- Vol. 15 (6) , 1206
Open AccessBCI-Inspired Adaptive Agents in Human–Robot Interaction: A Structural Framework for Coordinated Interaction Design
The accelerated integration of intelligent agents in user-centered digital environments has intensified research in the field of Human–Robot Interaction, especially regarding mechanisms for adaptive, intuitive, and cognitively aligned communication. The present study develops and empirically examines a structural model of BCI-inspired adaptive agents designed to support coordinated interaction in HRI contexts. The study analyzes users’ perceptions of standardized hypothetical interaction scenarios involving BCI-inspired adaptive digital agents, where BCI inspiration is conceptual and refers to adaptive architectures interpreting behavioral cues rather than direct neural signal acquisition. The proposed model integrates four main constructs—perceived technological innovation, user involvement, agent adaptivity, and digital synergy—and examines their associations with user satisfaction in digital collaborative environments. Data were collected through an anonymous questionnaire (N = 268) and analyzed using structural equation modeling with the PLS-SEM method. The structural model demonstrates substantial explanatory power, accounting for 66.8% of the variance in user satisfaction (R2 = 0.668). The study contributes by empirically supporting a scenario-based structural evaluation framework suitable for early-stage adaptive HRI system design. The results highlight the role of digital synergy in aligning innovation, engagement, and adaptive behavior in BCI-inspired adaptive HRI systems, providing directions for the design of adaptive robotic agents oriented toward coordinated interaction, user-centered integration, and responsible use in collaborative digital ecosystems.