ΜKLab participated in The Video Retrieval Competition 2024, with the VERGE system, an interactive video content retrieval system designed for browsing a collection of images extracted from videos and conducting targeted content searches. VERGE incorporates a variety of retrieval methods and fusion techniques. It also offers a user-friendly web application for query formulation and displaying top results. VBS is an international video content search competition that evaluates the state-of-the-art of interactive video retrieval systems.

S. I. Papadopoulos, C. Koutlis, S. Papadopoulos, P. C. Petrantonakis, “Similarity over Factuality: Are we making progress on multimodal out-of-context misinformation detection?.", in Proceedings of the WACV, 2025.

A. Spyros, A. Kougioumtzidou, A. Papoutsis, E. Darra, D. Kavallieros, A. Tziouvaras, T. Tsikrika, S. Vrochidis, I. Kompatsiaris, “A Comprehensive Survey of Manual and Dynamic Approaches for Cybersecurity Taxonomy Generation”, Knowledge and Information Systems, 2025

M. Lentzen, S. Vairavan, M. Muurling, V. Alepopoulos, A. Atreya, M. Boada, C. de Boer, P. Conde, J. Curcic, G. Frisoni, S. Galluzzi, M. T. Gjestsen, M. Gkioka, M. Grammatikopoulou, L. Hausner, C. Hinds, I. Lazarou, A. de Mendonça, S. Nikolopoulos, D. Religa, G. Scebba, P. J. Visser, G. Wittenberg, V. A. Narayan, N. Coello, A.K. Brem, D. Aarsland, H. Fröhlich on behalf of RADAR-AD, “RADAR-AD: assessment of multiple remote monitoring technologies for early detection of Alzheimer’s disease.

G. Karantaidis, A. Pantsios, I. Kompatsiaris, S. Papadopoulos, “IncSAR: A Dual Fusion Incremental Learning Framework for SAR Target Recognition.", in IEEE Access, vol. 13, pp. 12358-12372, 2025, doi: 10.1109/ACCESS.2025.3528633

G. Kirtsanis, G. Dolias, S. Kintzios, K. Ioannidis, S. Vrochidis, I. Kompatsiaris, “CNN-based Deep Auto-Encoders for Limited Gas Chromatography - Ion Mobility Spectrometry Data.", in Procceedings of the IEEE I2MTC – International Instrumentation and Measurement Technology Conference, Chemnitz, Germany, May 19-22, 2025, (Accepted for presentation).

SAFEGUARD aims at developing a next-generation holistic suite of tools that significantly improve LEA capabilities to protect public spaces against terrorist attacks through the entire lifecycle of their operations. To this end, SAFEGUARD leverages the successful outcomes of EU-funded projects (S4AllCities, CONNEXIONs, CREST, PREVISION, PRAETORIAN), providing a complete and powerful framework for intelligent threat detection relevant to the context of safety of public spaces. The outcomes of the project will result in the improvement of public spaces, such as malls, open crowded areas and events by deploying tools and technologies for acquiring intelligence regarding terrorist attacks and supporting LEA operations in an efficient and effective manner.

The monitoring and management of natural and man-made disasters has been a great issue in the Adriatic-Ionian region, as justified in the programme document and also underlined in the relevant policies addressed (EUSAIR, Green Deal, S3, etc). More specifically, AINATURE will focus on the use of AI tools (and contemporary technologies) for the early detection and monitoring of three major challenges faced by ADRION countries: - Pollution of open surface water resources and warning/monitoring of floods: through the adjustment of the AI tool developed in aqua3S and PathoCERT projects (H2020), the partners will be able to detect pollution and alterations in the water surface.

The European Security Data Space for Innovation (EU SDSI) has been recognized as the cornerstone for implementing the European Data Strategy in the security domain, aiming at Europe’s data sovereignty, while having as ultimate goal to increase trust in the use of Artificial Intelligence by Law Enforcement. In this context, TESSERA aims to conduct the preparatory work for the creation of high-quality large-scale trusted and shareable datasets based on identified operational use cases, thus supporting the European Security Data Space for Innovation.

ENSEMBLE aims to enhance the capabilities of multiple stakeholders involved in (cross-border) joint cybercrime-oriented investigations by developing (i) a modular AI-based forensically sound investigation ToolBox to assist LEAs in fighting sophisticated cyber-threats and cybercrimes, (ii) relevant training material for Police Authorities, prosecutors, and judicial actors involved in such investigations, and (iii) appropriate public awareness campaigns for early identification and prevention of cybercrimes MKLab is responsible for the coordination of the ENSEMBLE project and is also tasked with its Scientific and Technical management.