Paschalis Giakoumoglou

Research Assistant, Media Analysis, Verification and Retrieval Group (MeVer), Information Technologies Institute, Centre for Research and Technology Hellas (ITI-CERTH)

Biography

Paschalis Giakoumoglou is a Research Assistant in Media Analysis, Verification and Retrieval Group (MeVer) of the Information Technologies Institute at the Centre for Research and Technology Hellas (ITI-CERTH). His research interests include Time Series Forecasting, Deep Learning, Artificial Intelligence, Image Forensics and more.

News

• 25 June 2025: Paper accepted at ICCV 2025 (Hawaii, US)

Research Interests

Time Series Forecasting
Deep Learning
Artificial Intelligence
Image Forensics

Education

Aristotle University of Thessaloniki, Thessaloniki, Greece
Integrated MSc in Electrical and Computer Engineering
September 2019 — November 2024 | GPA: 9.42/10.00
Thesis: "Detection of Image Manipulations Created Using Convolutional Neural Networks and Diffusion Models", supervised by Prof. Panagiotis Petrantonakis
2nd Experimental School of Thessaloniki, Thessaloniki, Greece
High School Diploma
September 2016 — June 2019 | GPA: 19.9/20.0
Awarded for academic excellence in all years by the Ministry of Education

Papers

SAGI: Semantically Aligned and Uncertainty Guided AI Image Inpainting

P. Giakoumoglou, D. Karageorgiou, S. Papadopoulos, and P. C. Petrantonakis

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2025

[arXiv] [project] [code]

Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations

P. Giakoumoglou, M. Schinas, and S. Papadopoulos

Under review at ACM Transactions on Intelligent Systems and Technology, 2025

TGIF2: Extended Text-Guided Inpainting Forgery Dataset & Benchmark

H. Mareen, D. Karageorgiou, P. Giakoumoglou, P. Lambert, S. Papadopoulos, and G. Van Wallendael

Under review at EURASIP Journal on Information Security, 2025

SNAP: Synthetically Negative Augmented Pretraining for Vision-Language Models

N. Giakoumoglou, P. Giakoumoglou, K. M. Papadopoulos, A. Floros, and T. Stathaki

Under review

DiffusionPrint: Learning Generative Fingerprints for Diffusion-Based Inpainting Localization

P. Giakoumoglou and S. Papadopoulos

Under review