vera.ai: VERification Assisted by Artificial Intelligence

Livrables

Plan for dissemination, communication, clustering & exploitation activities

D61 will define target stakeholders and activities planned and already undertaken in T61 T62 and T63 incl supporting material The project website will be live from M3 latest and updated continuously

Annotation model, API definitions, and Database of Known Fakes first release

Documentation and code from T51 and first release of the DBKF

Data Management Plan

CERTH and ATC will lead the production of this report detailing how data in the project will be managed

Publications

Forensic Similarity for Source Camera Model Comparison

Auteurs: Marina Gardella, Pablo Musé
Publié dans: Image Processing On Line, 2022, ISSN 2105-1232
Éditeur: Image Processing On Line (ISSN 2105-1232)
DOI: 10.5201/ipol.2022.424

Image Forgery Detection via Forensic Similarity Graphs

Auteurs: Marina Gardella, Pablo Musé
Publié dans: Image Processing On Line, 2022, ISSN 2105-1232
Éditeur: Image Processing On Line (ISSN 2105-1232)
DOI: 10.5201/ipol.2022.432

Information Forensics and Security: A quarter-century-long journey

Auteurs: Mauro Barni, Patrizio Campisi, Edward Delp, Gwenael Doërr, Jessica Fridrich, Nasir Memon, Fernando Pérez-González, Anderson Rocha, Luisa Verdoliva, Min Wu
Publié dans: IEEE Signal Processing Magazine, 2023, ISSN 1053-5888
Éditeur: IEEE
DOI: 10.1109/MSP.2023.3275319

COVID-Related Misinformation Migration to BitChute and Odysee

Auteurs: Olga Papadopoulou; Evangelia Kartsounidou; Symeon Papadopoulos
Publié dans: Future Internet, 2022, ISSN 1999-5903
Éditeur: MDPI
DOI: 10.5281/zenodo.7389776

Auditing YouTube’s Recommendation Algorithm for Misinformation Filter Bubbles

Auteurs: Ivan Srba, Robert Moro, Matus Tomlein, Branislav Pecher, Jakub Simko, Elena Stefancova, Michal Kompan, Andrea Hrckova, Juraj Podrouzek, Adrian Gavornik, and Maria Bielikova
Publié dans: ACM Transactions on Recommender Systems, Numéro 1, 2023, ISSN 2770-6699
Éditeur: ACM Press
DOI: 10.1145/3568392

Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification

Auteurs: Razuvayevskaya, Olesya; Wu, Ben; Leite, João A.; Heppell, Freddy; Srba, Ivan; Scarton, Carolina; Bontcheva, Kalina; Song, Xingyi
Publié dans: PLOS ONE, 2024, ISSN 1932-6203
Éditeur: Public Library of Science
DOI: 10.48550/arXiv.2308.07282

Analysis and Experimentation on the ManTraNet Image Forgery Detector

Auteurs: Quentin Bammey
Publié dans: Image Processing On Line, 2022, ISSN 2105-1232
Éditeur: Image Processing On Line (ISSN 2105-1232)
DOI: 10.5201/ipol.2022.431

A Workflow to Detect, Monitor, and Update Lists of Coordinated Social Media Accounts Across Time: The Case of the 2022 Italian Election

Auteurs: Giglietto, Fabio; Marino, Giada; Mincigrucci, Roberto; Stanziano, Anna
Publié dans: Social Media + Society, 2023, ISSN 2056-3051
Éditeur: Sage
DOI: 10.1177/20563051231196866

Human and Machine Performance in Counting Sound Classes in Single-Channel Soundscapes

Auteurs: Jakob Abeßer, Asad Ullah, Sebastian Ziegler, Sascha Grollmisch
Publié dans: Journal of the Audio Engineering Society, Numéro 71, 2023, ISSN 1549-4950
Éditeur: Audio Engineering Society
DOI: 10.17743/jaes.2022.0106

Improving Synthetically Generated Image Detection in Cross-Concept Settings

Auteurs: Dogoulis, Pantelis; Kordopatis-Zilos, Giorgos; Kompatsiaris, Ioannis; Papadopoulos, Symeon
Publié dans: ACM International Workshop on Multimedia AI against Disinformation (MAD ’23), 2023
Éditeur: ACM
DOI: 10.5281/zenodo.7984285

ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness

Auteurs: Cegin, Jan; Simko, Jakub; Brusilovsky, Peter
Publié dans: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore, 2023, 2023
Éditeur: Association for Computational Linguistics
DOI: 10.48550/arxiv.2305.12947

On the detection of synthetic images generated by diffusion models

Auteurs: Riccardo Corvi, Davide Cozzolino, Giada Zingarini, Giovanni Poggi, Koki Nagano, Luisa Verdoliva
Publié dans: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023, 2023, ISBN 978-1-7281-6327-7
Éditeur: IEEE
DOI: 10.1109/ICASSP49357.2023.10095167

A Contrario Mosaic Analysis for Image Forensics

Auteurs: Bammey Quentin
Publié dans: Advanced Concepts for Intelligent Vision Systems (ACIVS), 2023
Éditeur: Springer
DOI: 10.5281/zenodo.8309383

Are classic forensic tools effective on satellite imagery?

Auteurs: Matthieu Serfaty, Tina Nikoukhah, Quentin Bammey, Rafael Grompone von Gioi, Carlo de Franchis
Publié dans: IEEE International Geoscience and Remote Sensing Symposium, 2023, ISSN 2153-7003
Éditeur: IEEE
DOI: 10.1109/IGARSS52108.2023.10282862

Towards an international standard to establish trust in media production, distribution and consumption

Auteurs: Frederik Temmermans; Sabrina Caldwell; Symeon Papadopoulos; Fernando Pereira; Philippe Rixhon
Publié dans: 24th International Conference on Digital Signal Processing, Numéro 24, 2023
Éditeur: IEEE
DOI: 10.5281/zenodo.7984567

MAD '23 Workshop: Multimedia AI against Disinformation

Auteurs: Luca Cuccovillo; Bogdan Ionescu; Giorgos Kordopatis-Zilos; Symeon Papadopoulos; Adrian Popescu
Publié dans: ACM International Conference on Multimedia Retrieval (ICMR), Thessaloniki, Greece, 12-15 June 2023, 2023, ISBN 979-8-4007-0178-8
Éditeur: ACM
DOI: 10.1145/3591106.3592303

Comparison of Multilingual Entity Linking Approaches

Auteurs: Ivelina Bozhinova, Andrey Tagarev
Publié dans: Proceedings of 2023 International Conference Recent Advances in Natural Language Processing. (pp. 224-233), 2023, ISBN 2603-28132023
Éditeur: INCOMA Ltd.
DOI: 10.26615/978-954-452-092-2_025

A Contrario Detection of H.264 Video Double Compression

Auteurs: Li, Yanhao; Gardella, Marina; Bammey, Quentin; Nikoukhah, Tina; Morel, Jean-Michel; Colom, Miguel; Grompone von Gioi, Rafael
Publié dans: International Conference in Image Processing (ICIP), 2023, ISSN 1522-4880
Éditeur: IEEE
DOI: 10.1109/ICIP49359.2023.10222775

Synthetic Misinformers: Generating and Combating Multimodal Misinformation

Auteurs: Stefanos-Iordanis Papadopoulos; Christos Koutlis; Symeon Papadopoulos; Panagiotis C. Petrantonakis
Publié dans: 2nd ACM International Workshop on Multimedia AI against Disinformation, ICMR, ACM (MAD'23), 2023
Éditeur: ACM
DOI: 10.5281/zenodo.7871280

TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization

Auteurs: Fabrizio Guillaro, Davide Cozzolino, Avneesh Sud, Nicholas Dufour, Luisa Verdoliva
Publié dans: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2023, 2023, ISSN 2575-7075
Éditeur: IEEE
DOI: 10.1109/CVPR52729.2023.01974

SheffieldVeraAI at SemEval-2023 Task 3: Mono and multilingual approaches for news genre, topic and persuasion technique classification

Auteurs: Wu, Ben; Razuvayevskaya, Olesya; Heppell, Freddy; Leite, João A.; Scarton, Carolina; Bontcheva, Kalina; Song, Xingyi
Publié dans: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), Numéro 17, 2023
Éditeur: Association for Computational Linguistics
DOI: 10.48550/arxiv.2303.09421

JADE OWL: JPEG 2000 forensics by wavelet offset consistency analysis

Auteurs: Quentin Bammey
Publié dans: International Conference on Image, Vision and Computing (ICIVC),, 2023
Éditeur: IEEE
DOI: 10.5281/zenodo.8119385

A Multi-Stream Fusion Network for Image Splicing Localization

Auteurs: Siopi, Maria; Kordopatis-Zilos, Giorgos; Charitidis, Polychronis; Kompatsiaris, Ioannis; Papadopoulos, Symeon
Publié dans: MMM 2023 - 29th Internatinal Conference on Multimedia Modeling, Numéro 29, 2023
Éditeur: Springer
DOI: 10.5281/zenodo.7322720

KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection

Auteurs: Timo Hromadka, Timotej Smolen, Tomas Remis, Branislav Pecher, Ivan Srba
Publié dans: Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), 2023
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.semeval-1.86

Intriguing properties of synthetic images: from generative adversarial networks to diffusion models

Auteurs: Riccardo Corvi, Davide Cozzolino, Giovanni Poggi, Koki Nagano, Luisa Verdoliva
Publié dans: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2023, 2023, ISSN 2160-7516
Éditeur: IEEE
DOI: 10.1109/CVPRW59228.2023.00104

Demosaicing to Detect Demosaicing and Image Forgeries

Auteurs: Quentin Bammey; Rafael Grompone Von Gioi; Jean-Michel Morel
Publié dans: 2022 IEEE International Workshop on Information Forensics and Security (WIFS), 2022, ISSN 2157-4774
Éditeur: IEEE
DOI: 10.1109/WIFS55849.2022.9975454

In-Depth Look at Word Filling Societal Bias Measures

Auteurs: Pikuliak, Matúš; Beňová, Ivana; Bachratý, Viktor
Publié dans: Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, Numéro 17, 2023
Éditeur: Association for Computational Linguistics
DOI: 10.48550/arxiv.2302.12640

MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark

Auteurs: Macko, Dominik; Moro, Robert; Uchendu, Adaku; Lucas, Jason Samuel; Yamashita, Michiharu; Pikuliak, Matúš; Srba, Ivan; Le, Thai; Lee, Dongwon; Simko, Jakub; Bielikova, Maria
Publié dans: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), Singapore, 2023, 2023
Éditeur: Association for Computational Linguistics
DOI: 10.48550/arxiv.2310.13606

Deepfake audio detection by speaker verification

Auteurs: Alessandro Pianese, Davide Cozzolino, Giovanni Poggi, Luisa Verdoliva
Publié dans: IEEE International Workshop on Information Forensics and Security (WIFS), 2022, ISSN 2157-4774
Éditeur: IEEE
DOI: 10.1109/WIFS55849.2022.9975428

Audio-Visual Person-of-Interest DeepFake Detection

Auteurs: Davide Cozzolino, Alessandro Pianese, Matthias Niessner, Luisa Verdoliva
Publié dans: IEEE Conference on Compurer Vision and Pattern Recognition (CVPR) Workshops 2023, 2023, ISSN 2160-7516
Éditeur: IEEE
DOI: 10.1109/CVPRW59228.2023.00101

Self-Supervised Video Similarity Learning

Auteurs: Giorgos Kordopatis-Zilos; Giorgos Tolias; Christos Tzelepis; Ioannis Kompatsiaris; Ioannis Patras; Symeon Papadopoulos
Publié dans: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023
Éditeur: IEEE
DOI: 10.1109/cvprw59228.2023.00504

Livrables

Publications

Partager cette page

Télécharger