I am an Associate Professor in the Department of Electrical and Computer Engineering at the University of Patras, Greece, where I lead the Interactive Technologies Laboratory. My research focuses on information systems & human–computer interaction, usable-security, and brain–computer interfaces. I serve as an Expert Member of the International Federation for Information Processing (IFIP), contributing to the Technical Committee TC-13 on Human–Computer Interaction. I also coordinate the Neuroengineering and Brain–Computer Interfaces Research Infrastructure at the University of Patras.
I have a strong track record in securing and managing competitive research funding, with about €7M in projects as Principal Investigator and Coordinator. My work has also been recognised through competitive research grants and international collaborations.
I am fluent in German, English and Greek.
EU Funded :: #neuroengineering #brain-computer interfaces #infrastructure #artifical intelligence
ELEVATE brings together the Neuroengineering and Brain-Computer Interfaces Research Infrastructure at the University of Patras (Coordinator), the Brain Data Group (University of Nottingham), and CYENS Centre of Excellence (Cyprus) to advance excellence in AI and neurotechnology, combining leading BCI expertise, advanced research infrastructure, and responsible AI innovation. The project will strengthen research capacity, support institutional reforms, boost digital and AI skills, and contribute to a Southern European hub of excellence aligned with the ERA Policy Agenda.
(€ 4,406,875, 2026-2030, Project Coordinator & Principal Investigator). Funding Agency: European Excellence Initiative (EEI), WIDERA (Horizon Europe)
National and EU Funded :: #brain-computer interfaces #infrastructure #artifical intelligence
The Neuroengineering and Brain-Computer Interfaces Research Infrastructure at the University of Patras aims to provide academic researchers, students, and external partners with access to a wide range of systems for non-invasive brain and eye-activity measurement. With a focus on portable and versatile equipment, the infrastructure enables studies in naturalistic environments and supports interdisciplinary research across fields such as health sciences, engineering, education, business, and the humanities.
(€265,000, 2025, Project Coordinator & Principal Investigator). Funding Agency: Greece 2.0 National Recovery and Resilience Plan & NextGenerationEU
More info: Research Infrastructure Website
National and EU Funded :: #vishing #cybersecurity #artifical intelligence
Sub 1.1. Excellence CRES Call, Greece - Topic: Digital Technologies - CyberSecurity: Design, Development, and Evaluation of an Integrated Information System and Real-Time Services for the Detection of Telephone Fraud (Vishing)
(€1,620,000, 2025-2027, Project Coordinator & Principal Investigator). Funding Agency: Hellenic Ministry of Education & NextGenerationEU
National Project AILA :: #phishing #cybersecurity #artifical intelligence #legal advice #information systems
Artificial Intelligence-driven Framework and Legal Advice Tools for Phishing Prevention and Mitigation in Information Systems
(€160,000, 2023-2025, Project Coordinator & Principal Investigator ). Funding Agency: Hellenic Foundation for Research and Innovation (H.F.R.I.).
More info: AILA Project Website
EU Project CREAMS :: #mixedreality #augmentedreality #virtualreality #artstudents #exhibitions
Scaffolding Creativity of Arts Students: Framework, Toolchain, and Educational Material on how to Create their Own Virtual Exhibitions
(€382,644, 2022-2025, Project Coordinator & Principal Investigator ). Funding Agency: European Commission.
More info: CREAMS Project Website
National Project CogniX :: #electroencephalography #eyetracking #cognition
Electroencephalography and Eye Gaze-driven Framework for Intelligent and Real-Time Human Cognitive Modelling (€194,295, 2022-2024, Project Coordinator & Principal Investigator ).
Funding Agency: Hellenic Foundation for Research and Innovation (H.F.R.I.).
More info: COGNIX Project Website
EU Project TRUSTID :: #cybersecurity #userauthentication #biometrics
Intelligent and Continuous Online Student Identity Management for Improving Security and Trust in European Higher Education Institutions
(€291,310, 2021-2023, Project Coordinator & Principal Investigator ). Funding Agency: European Commission.
More info: TRUSTID Project Website
National Project DeAR Museum :: #mixedreality #virtualreality #culturalheritage
Development and production of augmented and virtual reality applications supporting narrative tours at the Tomato Industrial Museum in order to convey a
personalized experience to the visitors of an old factory (€300,000, 2021-2023, Principal Investigator).
Funding Agency: Research-Create-Innovate.
More info: DeAR Museum Project Website
[High Performance Computing (HPC) infrastructure - April 2026]
We are excited to announce the launch of a state-of-the-art High-Performance Computing (HPC) system, significantly enhancing our research and applied capabilities in Artificial Intelligence (AI) and Machine Learning (ML).
🔹The system delivers cutting-edge computational power powered by next-generation GPUs (Ada Lovelace architecture with a total of 192 GB GPU memory), with scalability up to approximately 2 TB of GPU memory, supporting demanding AI and HPC workloads. It is complemented by multi-core Intel Xeon Scalable processors, high-capacity memory (≥512 GB DDR5), ultra-fast NVMe storage, and high-performance networking (≥25 GbE), forming a robust and scalable computing environment.
🔹Importantly, the system achieves a very low energy footprint (PUE < 1.2), enabled by advanced single-phase immersion cooling technology (open bath), ensuring high energy efficiency and operational reliability.
🔹This infrastructure unlocks new opportunities for developing and training advanced machine learning and deep learning models, supporting computationally intensive applications, enabling real-time big data analytics, and fostering interdisciplinary collaborations and research initiatives.
The equipment was funded under the project “SUB1.1: Clusters of Research Excellence (CREs)”, titled “CyberShield_YP3TA-0560177: An Integrated Information System, Tools, and Smart Real-Time Services for the Detection and Mitigation of Cyberattacks via Voice Calls (Vishing)”.
I’m pleased to announce that from March 29th to April 3rd we are hosting the EESTEC LC Patras international workshop entitled "BrAIn's Anatomy: From Brain Signals to Insight".
This event will bring together 11 participants from Universities across Europe and 9 local students to explore the intersection of brain signals and engineering.
Designed especially for early-level Engineering students, this one-week workshop introduces participants to neurotechnology and the full data processing pipeline behind brain measurements.
I’m pleased to announce that our project ELEVATE has entered the Grant Agreement Preparation phase, achieving a perfect 15/15 score and being selected among the top 17 proposals out of 267 submissions.
ELEVATE brings together the Neuroengineering and Brain-Computer Interfaces Research Infrastructure at the University of Patras, the Brain Data Group (University of Nottingham), and CYENS Centre of Excellence (Cyprus) to advance excellence in AI and neurotechnology, combining leading BCI expertise, advanced research infrastructure, and responsible AI innovation.
The project will strengthen research capacity, support institutional reforms, boost digital and AI skills, and contribute to a Southern European hub of excellence aligned with the ERA Policy Agenda.
I’m pleased to share that I coordinate the Neuroengineering and Brain–Computer Interfaces Research Infrastructure at the University of Patras.
The infrastructure is supported by the Deanships of the participating Schools—
Engineering,
Humanities and Social Sciences,
Health Sciences, Health Rehabilitation Sciences,
Business and Economics.
Our aim is to provide academic researchers, students, and external partners with access to a broad suite of systems for non-invasive measurement of brain and eye activity.
Emphasizing portable equipment, the infrastructure enables studies in naturalistic settings and supports ecological valid research activities.
We’re excited to share that our paper "Strengthening Graphical Password Security Through EEG-Driven Classifiers Based on Image Content Familiarity" has been published at the International Journal of Human-Computer Interaction, 2025.
- Impact Factor: 4.920
Abstract:
The development of reliable authentication schemes faces significant challenges due to security vulnerabilities, like shoulder-surfing and impersonation attacks. In this article, we present a six-month in-lab study (N = 30), on a novel two-factor authentication prototype combining Microsoft’s Picture Gesture Authentication (PGA) with Electroencephalography (EEG). The premise of this study was to explore the users’ unique neural responses that are triggered during the authentication process to train individual AI models that would mitigate impersonation attacks. We also investigated whether users’ familiarity with the PGA’s background image affects the authentication accuracy. Participants completed 20 trials using familiar and unfamiliar background images. Results indicate that familiar stimuli and users’ muscle activity improve cognitive efficiency and authentication accuracy. Additionally, combining time-frequency domain features with Support Vector Machines, yielded optimal results. These findings highlight the potential of utilizing EEG-based technology in graphical authentication systems, offering secure and user-friendly alternatives to traditional methods.
DOI: https://doi.org/10.1080/10447318.2025.2504195
[Publication - ERCIM News - April 2025]
CulturAI: Advancing Mixed Reality Art Experiences
with Large Language Models
We’re excited to share that our latest work has been published in ERCIM News-
“AI for Cultural Heritage”.
This publication highlights our efforts in combining AI and Mixed Reality to enrich cultural experiences. We explore how Large Language Models can enhance engagement with cultural heritage through intelligent interaction.
By bridging Mixed Reality displays, real-time LLM-driven dialogue, and cultural storytelling,
CulturAI demonstrates how technological innovation can expand access to the arts and transform
learning experiences in museum and heritage contexts.
Clieck here to read the article
[Publication - EuroSec'25: Proceedings of the 18th European Workshop on Systems Security - March 2025]
Enhancing Graphical Authentication with EEG: A Study on Neural Responses and AI-Driven Security
Can brain activity enhance authentication? This study combines Microsoft’s Picture Gesture Authentication (PGA) with EEG, using neural responses to train AI models against impersonation attacks. Findings show that familiar images improve accuracy, muscle activity aids password input, and EEG features enhance security, paving the way for a more secure authentication.
DOI: https://doi.org/10.1145/3722041.3723103
[Publication - Oct 2024]
“The Regulation of Large Language Models (LLMs) in Regulation (EU) 2024/1689 on Artificial Intelligence and the GDPR”
This study introduces the legal issues arising from the regulation of Large Language Models (LLMs) in Regulation (EU) 2024/1689 on Artificial Intelligence and the General Data Protection Regulation. It highlights that with technological advancements, the capabilities of dialogue models are continuously improving, allowing them to generate more accurate and complex responses. However, ethical and transparency issues remain regarding how they are used and the impacts they may have on society, especially concerning privacy protection and ensuring objectivity in the processing of personal data.”
Download the article (in Greek)
[Research Prototype - August 2024]
“CogniX: Electroencephalography and Eye Gaze-driven Framework for Intelligent and Real-Time Human Cognitive Modelling”- Funding Agency: Hellenic Foundation for Research and Innovation (H.F.R.I.).
We have finalized the research prototype at a TRL-4 of CogniX. This work investigates human cognitive styles and factors, which are essential for creating systems that adapt dynamically to individual users. By leveraging EEG and eye-gaze analysis, this approach enables a deeper understanding of user cognition, offering insights into how individuals process information and make decisions. Modeling these factors allows for the development of personalized user interfaces, facilitating more effective information processing and tailored decision support. These cognitive models further inform the design of user experiences that cater to diverse cognitive styles, a valuable strategy across educational and cultural domains, where adaptable interaction with information systems enhances engagement and personalization.
[Best Demo Paper Award - July 2024]
We received the ACM UMAP Best Demo Award of 2024 for our paper entitled "CulturAI: Exploring Mixed Reality Art Exhibitions with Large Language Models for Personalized Immersive Experiences": ACM - Digital Library.
Abstract: Mixed Reality (MR) technologies have transformed the way in which we interact and engage with digital content, offering immersive experiences that blend the physical and virtual worlds. Over the past years, there has been increasing interest in employing Artificial Intelligence (AI) technologies to improve user experience and trustworthiness in cultural contexts. However, the integration of Large Language Models (LLMs) into MR applications within the Cultural Heritage (CH) domain is relatively underexplored. In this work, we present an investigation into the integration of LLMs within MR environments, focusing on the context of virtual art exhibitions. We implemented a HoloLens MR application, which enables users to explore artworks while interacting with an LLM through voice. To evaluate the user experience and perceived trustworthiness of individuals engaging with an LLM-based virtual art guide, we adopted a between-subject study design, in which participants were randomly assigned to either the LLM-based version or a control group using conventional interaction methods. The LLM-based version allows users to pose inquiries about the artwork displayed, ranging from details about the creator to information about the artwork’s origin and historical significance. This paper presents the technical aspects of integrating LLMs within MR applications and evaluates the user experience and perceived trustworthiness of this approach in enhancing the exploration of virtual art exhibitions. Results of an initial evaluation provide evidence about the positive aspect of integrating LLMs in MR applications. Findings of this work contribute to the advancement of MR technologies for the development of future interactive personalized art experiences.
https://doi.org/10.1145/3631700.3664874
[Publication - March 2024]
"A Systematic Review
and Research Challenges on Phishing Cyberattacks from an
Electroencephalography and Gaze-based perspective", co-authored by George Thomopoulos and Dr. Lyras Dimitrios, in Personal Ubiquitous Computing - Springer.
Abstract:
Phishing is one of the most important security threats in modern Information Systems causing different levels of damages to end-users and service providers such as financial and reputational losses. State-of-the-art anti-phishing research is highly fragmented and monolithic and does not address the problem
from a pervasive computing perspective. In this survey, we aim to contribute to
the existing literature by providing a systematic review of existing experimental
phishing research that employs EEG and eye-tracking methods within multi-
modal and multi-sensory interaction environments. The main research objective of this review is to examine articles that contain results of at least one EEG-based
and/or eye-tracking based experimental setup within a phishing context. The database search with specific search criteria yielded 651 articles from which, after
the identification and the screening process, 42 articles were examined as per the
execution of experiments using EEG or eye-tracking technologies in the context
of phishing. This survey is approaching the subject across the following pillars: a)
the experimental design practices with an emphasis on the applied EEG and eye-
tracking acquisition protocols; b) the artificial intelligence and signal preprocessing techniques that were applied in those experiments and finally c) the
phishing attack types examined. We also provide a roadmap for future research
in the field by suggesting ideas on how to combine state-of-the-art gaze-based
mechanisms with EEG technologies for advancing phishing research. This leads to a discussion on the best practices for designing EEG and Gaze-based frameworks.
[Publication - January 2024]
" A Comprehensive Survey of EEG Preprocessing Methods for Cognitive Load Assessment", in IEEE Access journal. We are grateful for the support provided by the Hellenic Foundation for Research and Innovation (H.F.R.I.). (Grant Number: 3849 - Eye Gaze driven Framework for Intelligent and Real-Time Human Cognitive Modeling - CogniX).
Abstract: Preprocessing electroencephalographic (EEG) signals during computer-mediated Cognitive Load tasks is crucial in Human-Computer Interaction (HCI). This process significantly influences subsequent EEG analysis and the efficacy of Artificial Intelligence (AI) models employed in Cognitive Load Assessment. Consequently, it stands as an indispensable procedure for developing dependable systems capable of adapting to users’ cognitive capacities and constraints. We systematically analyzed fifty-seven (57) research papers on computer-mediated Cognitive Load EEG experiments published between 2018 and 2023. The preprocessing methods identified were multiple, controversial, and strongly dependent on the particularities of each experiment and the derived experimental dataset. Our investigation involved the meticulous classification of preprocessing methods based on distinct parameters, namely the degree of user intervention, the noise level, and the subject pool size. Particular attention was paid to semi-automated denoising technology since conventional methods, advanced approaches, and standardized pipelines overwhelm research, but no optimum solution is available yet. This survey is anticipated to provide a valuable contribution to the rising demand for an efficient and fully automated preprocessing approach in EEG-based computerized Cognitive Load experiments.
The integration of Large Language Models (LLMs) into MR applications within the Cultural Heritage (CH) domain is relatively underexplored. In this work, we present an investigation into the integration of LLMs within MR environments, focusing on the context of virtual art exhibitions. We implemented a HoloLens MR application, which enables users to explore artworks while interacting with an LLM through voice (https://doi.org/10.1145/3631700.366487 ). This work received the ACM UMAP 2024 Best Demo Award of 2024 (July 2024).
In this work, we have designed and developed CogniX, an extensible tool for human cognitive modeling. This work investigates human cognitive styles and factors, which are essential for creating systems that adapt dynamically to individual users. By leveraging EEG and eye-gaze analysis, this approach enables a deeper understanding of user cognition, offering insights into how individuals process information and make decisions. Modeling these factors allows for the development of personalized user interfaces, facilitating more effective information processing and tailored decision support. These cognitive models further inform the design of user experiences that cater to diverse cognitive styles, a valuable strategy across educational and cultural domains, where adaptable interaction with information systems enhances engagement and personalization.
In this work, we have designed and developed CogniKit, an extensible tool for human cognitive modeling. It is based on the analysis, classification and visualization of eye tracking data such as gaze points, fixation count and duration, saccades, gaze transition and stationary entropy, heat maps, areas of interests, etc. These are further processed, analyzed and classified for detecting higher level human cognitive factors such as cognitive processing styles and abilities. CogniKit comprises of two main components: i) a software application that collects and processes low- and high-level eye gaze data metrics in real-time; and ii) an extensible interactive workbench for storing, analyzing, classifying and visualizing the collected eye gaze data.
Relevant paper: ACM WI 2019, ACM IUI 2020
Mixed reality technologies embrace hand gesture-based interaction modalities, which can be leveraged by picture passwords, as they require users to draw secret gestures on a background image. In this work, we have designed and developed HoloPass, a novel mixed reality application that utilizes the Microsoft HoloLens device that allows users to directly interact with picture-based holograms in order to perform user authentication tasks. The current prototype was developed in Unity 3D, using C# and Microsoft's Mixed Reality Toolkit for HoloLens, and follows implementation guidelines of Microsoft Windows 10 Picture Gesture Authentication in which users draw three secret gestures on a background image that acts as a cue.
Relevant papers: ACM CHI 2019, INTERACT 2019
This work aims at scaffolding end-users in improving the security of graphical passwords through a playful interaction design in mixed reality. For doing so, we elaborated on a playful interaction de-sign framework and developed, based on it, an experimental mixed reality (MR) application that deployed multi-modal and playful user interaction experiences. A user evaluation woth 30 participants revealed that introducing playful characteristics in the design of MR graphical passwords had a catalyst effect on the security of user generated passwords and simultaneously affected significantly end-users' perceptions and understanding related to security semantics of graphical passwords.
Associate Professor (2023-) at the Department of Electrical and Computer Engineering, University of Patras
Assistant Professor (2021-2023) at the Department of Electrical and Computer Engineering, University of Patras
Assistant Professor (2016-2020), Tenure-track Lecturer (2013-2016) at the Department of Cultural Heritage and New Technologies, University of Patras
Visiting Assistant Professor at the Department of Computer Science, University of Cyprus (2011-2013)
Adjunct Lecturer at the University of Patras, University of Ioannina, Technical Institute of Patras (2004-2011)
I am always happy to discuss with prospective students new research endeavors in the areas of Information Systems and Culture, Modelling Human Cognition in Interactive Systems, and Usable Security. If you are interested to discuss your research idea please don't hesitate to contact me at fidas AT upatras.gr
Suggested Topics for Ph.D.