Fabrizio Guillaro is a Research Fellow at the University Federico II of Naples, Italy, in the Image Processing Research Group (GRIP). He completed his PhD in February 2025. His main research interests focus primarily on multimedia forensics, with a particular emphasis on the development of deep-learning techniques to detect local manipulations in digital images and identify AI-generated content. He is working under the direction of Professor Luisa Verdoliva and Professor Giovanni Poggi and his current research is being conducted in collaboration with Google Research / Google DeepMind since 2021. He interned at Google Research as a PhD Student Researcher from October 2023 to May 2024 in the Media Integrity team (Mint), addressing the challenge of out-of-distribution data in the context of Generative AI detection. He graduated in Computer Engineering in 2021 at University of Naples Federico II with a thesis focused on the development of a semantic-based approach for image forgery detection. He participated in the 2018 IEEE Signal Processing Cup on camera model identification, earning the first prize after presenting his team's work in ICASSP 2018.
Work Experience
2024 - present: Postdoctoral Researcher at UniNA
2023-2024: Ph.D. Student Researcher at Google Research
Education
2021-2024: Ph.D. in Information Technologies and Electrical Engineering, at Image Processing Research Group (GRIP) - University of Naples Federico II, Italy
2018–2021: MSc. in Computer Engineering, University of Naples Federico II, Italy
2014–2018: BSc. in Computer Engineering, University of Naples Federico II, Italy
Awards
2018: UniNa Outstanding Student
2018: Winner of the IEEE Signal Processing Cup - Prize: US$ 5.000.
2018: IEEE Forensic Camera Model Identification Challenge – 3rd place (out of 582) on Kaggle - Prize: US$ 5.000.
Publications
F. Guillaro, G. Zingarini, B. Usman, A. Sud, D. Cozzolino, L. Verdoliva, “A Bias-Free Training Paradigm for More General AI-generated Image Detection”, in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2025
V. De Rosa, F. Guillaro, G. Poggi, D. Cozzolino, L. Verdoliva , “Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection”, in IEEE International Workshop on Information Forensics and Security (WIFS), December 2024
F. Guillaro, D. Cozzolino, G. Poggi, L. Verdoliva , “Uncertainty-driven detection and localization of image forgeries”, Chapter in CNIT Volume. Series: Signal Processing and Learning for Next Generation Multimedia, pp. 145-164, 2024
F. Guillaro, D. Cozzolino, A. Sud, N. Dufour, L. Verdoliva, “TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization”, in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 20606-20615, June 2023
H. Mareen, D. Vanden Bussche, F. Guillaro, D. Cozzolino, G. Van Wallendael, P. Lambert, L. Verdoliva, “Comprint: Image Forgery Detection and Localization using Compression Fingerprints,” in International Conference on Pattern Recognition (ICPR) workshops, August 2022
Technical Program Committees
2025: IEEE/CVF International Conference on Computer Vision (ICCV)
2025: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2025: ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec)
2023-2024: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2022-2024: IEEE/CVF CVPR Workshop on Multimedia Forensics
Reviewer: International Journals
2023-2025: Transactions on Information Forensics and Security (TIFS)
2024: IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
2024: International Journal of Computer Vision (IJCV)
2022: Springer’s Multimedia Systems journal
Organizer
MediaEval 2025 Challenge (Task: “Synthetic Images: Advancing detection of generative AI used in real-world online images”)
Projects
2024-present: vera.ai, a research project focusing on disinformation analysis and AI supported verification,
funded by EU’s Horizon Europe, Innovate UK, and the Swiss State SERI
2021-2024: DISCOVER (a Data-driven Integrated Approach for Semantic InCOnsistencies VERification), funded by
DARPA within the SEMAFOR (Semantic Forensics) initiative
