Veselina Georgieva Spasova

Dr. Veselina Georgieva Spasova

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2021 in IOP Conference Series: Materials Science and Engineering
Verified
Conference Paper
Open access
PDF file
VSVeselina Georgieva Spasova
Veselina Georgieva Spasova
BGB G Georgiev
B G Georgiev
PSP D Stefanov
P D Stefanov
BSB P Stoyanov
B P Stoyanov
The preservation of cultural and historical monuments aims to draw public attention to the national heritage, which preserves history and traditions and distinguishes us from other nations. The preservation, restoration and maintenance of any historical monument require skills, knowledge, resources, time and effort. The aim of this article is to present developing a prototype of an early warning system for disasters, mounted on a biggest monument in Varna from the socialist history period. This multidisciplinary project consists of two parts-creating a model of the monument at a scale of 1:20 and installing an IoT based solution, built of sensors and controllers.

1 January 2022 in AIP Conference Proceedings
Verified
Conference Paper
Open access
PDF file
TBTeodora Bakardjieva
Teodora Bakardjieva
VSVeselina Georgieva Spasova
Veselina Georgieva Spasova
Antonina IvanovaAntonina Ivanova
Antonina Ivanova
EREvgeniya Rakitina
Evgeniya Rakitina
More than ever, society accepts the knowledge-sharing frameworks, remote work, empathetic design, and the importance of trust in co-creation and the practical necessity of knowledge management (KM) proved its relevance for universities. KM 4.0 is enabling the application of digital technologies work towards an inclusion vision of Society 5.0. With the arrival of Industry 4.0, the scenario of various intelligent agents interacting reliably and securely with each other becomes a reality which learning systems need to address. In this paper an open agent-based modular framework for personalized and adaptive curriculum generation in an e-learning environment is proposed. The presented framework enables integration of different types of expert agents, various kinds of learning objects and user modelling techniques. It creates possibilities for adaptive e-learning processes where knowledge emerges as a result of the ongoing collaborative process. All participants in the system are peers who collaborate in knowledge creation, integration and distribution. A user profile and knowledge base are maintained with the help of software agents. Other agents carry the responsibility for finding the best peer to answer a question, and for managing knowledge resources. The KM e-learning system is used for supporting the educational process at the Varna Free University.

29 June 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ACAnton Chagovec
Anton Chagovec
TBTeodora Bakardjieva
Teodora Bakardjieva
Antonina IvanovaAntonina Ivanova
Antonina Ivanova
Fatima SapundzhiFatima Sapundzhi
Fatima Sapundzhi
VSVeselina Georgieva Spasova
Veselina Georgieva Spasova
AIAndriana Ivanova
Andriana Ivanova
The increasing adoption of cloud computing has expanded organizational attack surfaces and created additional opportunities for identity abuse, ransomware operations, data exposure, and configuration-related security incidents. Conventional monitoring environments based primarily on static rules, fragmented telemetry, and manual triage often struggle to prioritize high-severity incidents in real time. This study evaluates the operational impact of an integrated AI-augmented cloud-native SIEM/XDR/SOAR architecture for cloud threat detection and automated incident response. A sequential mixed-methods comparative case study was conducted across two enterprise-style security environments: an AI-augmented architecture combining cloud-native SIEM, XDR telemetry unification, behavioral analytics, AI-assisted correlation, generative-AI analyst support, and SOAR automation, and a conventional baseline environment based on manual triage and signature-based controls. Three attack scenarios were analyzed: phishing-led account takeover, multi-stage ransomware, and shadow-IT data exfiltration. The AI-augmented architecture reduced mean time to triage from 17.4 h in the conventional baseline to 10.7 min and enabled ransomware containment in under five minutes through pre-configured automated response playbooks. The results also showed improved prioritization of high-severity incidents, reduced analyst review burden, and a high automated closure rate. The findings provide operational evidence for the evaluated security architecture. Limitations include single-vendor dependency, non-equivalent false-positive classification mechanisms, proprietary model internals, calibration requirements, and detection gaps involving legitimate third-party services and password-protected content.


20 May 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
ACAnton Chagovec
Anton Chagovec
TBTeodora Bakardjieva
Teodora Bakardjieva
Antonina IvanovaAntonina Ivanova
Antonina Ivanova
Fatima SapundzhiFatima Sapundzhi
Fatima Sapundzhi
VSVeselina Georgieva Spasova
Veselina Georgieva Spasova
AIAndriana Ivanova
Andriana Ivanova
The increasing adoption of cloud computing has expanded organizational attack surfaces and increased exposure to credential compromise, ransomware, and cloud misconfiguration. Conventional security information and event management (SIEM) systems, based primarily on static correlation rules and signature-based detection, often struggle to process heterogeneous cloud telemetry and prioritize high-severity incidents in real time. This study evaluates the operational impact of an artificial intelligence (AI)-augmented SIEM and Extended Detection and Response (XDR) architecture for cloud threat detection and automated incident response. A mixed-methods comparative case study was conducted across two enterprise-style security environments: an AI-augmented cloud-native SIEM/XDR architecture and a conventional baseline environment based on manual triage and signature-based controls. Three attack scenarios were analyzed: phishing-led account takeover, multi-stage ransomware, and shadow-IT data exfiltration. The AI-augmented environment reduced mean time to triage from 17.4 hours in the conventional baseline to 10.7 minutes and enabled ransomware containment in under five minutes through automated response playbooks. The results also showed improved prioritization of high-severity incidents, reduced analyst workload, and a high automated closure rate. However, limitations were observed in the calibration of behavioral models, vendor dependency, and detection gaps involving legitimate third-party services and password-protected content. The findings should be interpreted as operational evidence at an architectural level, not as an isolated evaluation of individual AI models.