AI-based-technologies for trustworthy solutions against disinformation

Informazioni relative al progetto

AI4TRUST

ID dell’accordo di sovvenzione: 101070190

DOI

10.3030/101070190

Progetto chiuso

Data della firma CE 6 Dicembre 2022

Data di avvio 1 Gennaio 2023

Data di completamento 28 Febbraio 2026

Finanziato da

• Digital, Industry and Space

Costo totale

€ 5 950 682,50

Contributo UE

€ 5 950 682,50

Coordinato da

FONDAZIONE BRUNO KESSLER
Italy

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Risultati finali

Documents, reports (10)

Design of the methodological toolbox

The consortium will agree upon the exact design of the set of data-driven, model-driven and AI-driven tools that will be tailored and integrated between themselves to specifically serve the needs of the AI4TRUST platform and ecosystem.

Pilot planning report

This deliverable will illustrate the detailed piloting requirements, planning, and KPI definition.

AI4TRUST Platform Specification

This deliverable will provide the system specifications as detailed in T5.1. The initial release will focus on the most relevant components and will be progressively updated to reflect the evolution of the AI4TRUST APIs.

Explainability and Transparency report and AI tools

This deliverable will report results of T4.1-T4.2 to outline the explainability and transparency needs for the AI4TRUST platform and the socio-linguistic, user contextual, and social network factors of design for disinformation and mitigating misinformation. It will also include the first version of Trustworthy AI algorithms produced in T4.3.

Pilot planning report - Revised version

This deliverable will provide an updated version of D6.1, revised according to the recommendations given by the external experts at the RP1 review.

First report on social dynamics of misinformation

This deliverable will report the first version of the findings of T4.1 on the socio-contextual basis for misinformation.

Piloting sessions report v1

This deliverable describes the experimentation and validation of the AI4TRUST Platform v1 and v2-3 through its usage in the three piloting sessions. It includes an update of the planning and methodology devised in T6.1.

AI4TRUST Communication and Dissemination Plan

Strategic document setting the communication and dissemination strategy of the project, including key indicators, roles and responsibilities.

Communication and Dissemination Report v1

The v1 (M20) will include some results of the first half of the project communication and dissemina-tion activities, also including i) the clustering activities within T7.4; ii) the Kick-off Conference and Stakeholder Workshop (M18). The final version of this deliverable (M36) will contain the final results including: i) the proceedings of the Final Stakeholder Forum and Policy Workshop, and iii) the reach of the SKYTG24 miniseries.

Platform Specification -- Revised version

This deliverable will provide an updated version of D5.4, revised according to the recommendations given by the external experts at the RP1 review.

Other (4)

First release of AI tools for disinformation detection

This deliverable will include the first release of T3.1-T3.4 and will also report on the exposed APIs for the integration of some of these technologies in the AI4TRUST platform.

Ground truth data and social listening data streams

The access to ground data collected by the Human Fact-Checking network, as well as the one collected from social listening data streams, will be provided, in the earliest stages of the project to all technical members of the consortium to bootstrap the R&D.

AI4TRUST Platform v1

This deliverable constitutes the initial release of the AI4TRUST platform. It will also include the adopted ethical, privacy and data protection compliance technical measures as defined in T5.2 and will formalise the availability of the most relevant components. The SW modules, as well as the platform specification devised in T5.1, will be enhanced and updated at M32 (Enhanced version).

AI4TRUST Platform v2

This deliverable constitutes the enhanced release of the AI4TRUST platform. It will also include the updated ethical, privacy and data protection compliance technical measures as defined in T5.2 and will formalise the availability of the most relevant components. The SW modules, as well as the platform specification devised in T5.1 and T5.2, will be enhanced and updated at M38 (Final version).

Pubblicazioni

Peer reviewed articles (25)

PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor

Autori: Goel, Vidit; Peruzzo, Elia; Jiang, Yifan; Xu, Dejia; Xu, Xingqian; Sebe, Nicu; Darrell, Trevor; Wang, Zhangyang; Shi, Humphrey
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, ISSN 2575-7075
Editore: IEEE
DOI: 10.48550/ARXIV.2303.17546

Improved visually prompted keyword localisation in real low-resource settings

Autori: Nortje, Leanne; Oneata, Dan; Pirlogeanu, Gabriel; Kamper, Herman
Pubblicato in: 2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD), 2025, ISSN 2771-5787
Editore: 2025 International Conference on Speech Technology and Human-Computer Dialogue (SpeD)
DOI: 10.48550/ARXIV.2409.06013

Weakly-supervised deepfake localization in diffusion-generated images

Autori: Țânțaru, Dragoș–Constantin; Oneață, Elisabeta; Oneață, Dan
Pubblicato in: 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, ISSN 2642-9381
Editore: IEEE
DOI: 10.48550/ARXIV.2311.04584

Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization

Autori: Zhao Y.; Zhong Z.; Zhao N.; Sebe N.; Lee G. H.
Pubblicato in: International Journal of Computer Vision, 2023, ISSN 0920-5691
Editore: Kluwer Academic Publishers
DOI: 10.48550/arxiv.2212.09068

Visually Grounded Speech Models Have a Mutual Exclusivity Bias

Autori: Nortje, Leanne; Oneață, Dan; Matusevych, Yevgen; Kamper, Herman
Pubblicato in: Transactions of the Association for Computational Linguistics, 2024, ISSN 2307-387X
Editore: Transactions of the Association for Computational Linguistics
DOI: 10.48550/ARXIV.2403.13922

A Survey on Automatic Credibility Assessment Using Textual Credibility Signals in the Era of Large Language Models

Autori: Srba, I.; Razuvayevskaya, O.; Leite, J.A.; Moro, R.; Schlicht, I.B.; Tonelli, S.; García, F.M.; Lottmann, S.B.; Teyssou, D.; Porcellini, V.; Scarton, C.; Bontcheva, K.; Bielikova, M.
Pubblicato in: ACM Transactions on Intelligent Systems and Technology, 2026, ISSN 2157-6912
Editore: Association for Computing Machinery
DOI: 10.48550/ARXIV.2410.21360

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

Autori: Matteo Farina; Massimiliano Mancini; Elia Cunegatti; Gaowen Liu; Giovanni Iacca; Elisa Ricci 0001
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, ISSN 2575-7075
Editore: IEEE
DOI: 10.48550/ARXIV.2404.05621

Novel Class Discovery for Ultra-Fine-Grained Visual Categorization

Autori: Liu, Yu; Cai, Yaqi; Jia, Qi; Qiu, Binglin; Wang, Weimin; Pu, Nan
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, ISSN 2575-7075
Editore: IEEE
DOI: 10.48550/ARXIV.2405.06283

TGIF2: extended text-guided inpainting forgery dataset and benchmark

Autori: Hannes Mareen, Dimitrios Karageorgiou, Paschalis Giakoumoglou, Peter Lambert, Symeon Papadopoulos, Glenn Van Wallendael
Pubblicato in: Journal on Information Security, 2026, ISSN 3091-4515
Editore: Springer Science and Business Media LLC
DOI: 10.1186/S13635-026-00235-9

FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation

Autori: Zhao, Dong; Li, Jinlong; Wang, Shuang; Wu, Mengyao; Zang, Qi; Sebe, Nicu; Zhong, Zhun
Pubblicato in: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, ISSN 2575-7075
Editore: IEEE
DOI: 10.48550/ARXIV.2503.17940

Efficient Training Strategies for Natural Sounding Speech Synthesis and Speaker Adaptation Based on Fastpitch

Autori: Stan, Adriana; Ragman, Teodora
Pubblicato in: 2024 IEEE 20th International Conference on Intelligent Computer Communication and Processing (ICCP), 2024, ISSN 2766-8495
Editore: IEEE
DOI: 10.5281/ZENODO.13985555

Hybrid-Diarization System with Overlap Post-Processing for the DISPLACE 2024 Challenge

Autori: Pîrlogeanu, Gabriel; Pascu, Octavian; Georgescu, Alexandru Lucian; Cucu, Horia
Pubblicato in: Interspeech 2024, 2024, ISSN 2958-1796
Editore: Interspeech 2024
DOI: 10.21437/INTERSPEECH.2024-1287

On the conversational persuasiveness of GPT-4

Autori: Francesco Salvi; Manoel Horta Ribeiro; Riccardo Gallotti; Robert West
Pubblicato in: Nature Human Behaviour, 2025, ISSN 2397-3374
Editore: Nature Human Behaviour (Nat Hum Behav)
DOI: 10.1038/S41562-025-02194-6

Towards generalisable and calibrated audio deepfake detection with self-supervised representations

Autori: Pascu, Octavian; Stan, Adriana; Oneață, Dan; Oneață, Elisabeta; Cucu, Horia
Pubblicato in: Interspeech 2024, 2024, ISSN 2958-1796
Editore: Interspeech 2024
DOI: 10.5281/ZENODO.12526792

Decoding the News Media Diet of Disinformation Spreaders

Autori: Bertani, Anna; Mazzeo, Valeria; Gallotti, Riccardo
Pubblicato in: Entropy, 2024, ISSN 1099-4300
Editore: Multidisciplinary Digital Publishing Institute (MDPI)
DOI: 10.3390/E26030270

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages

Autori: Farina, Matteo; Mancini, Massimiliano; Iacca, Giovanni; Ricci, Elisa
Pubblicato in: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, ISSN 2575-7075
Editore: IEEE
DOI: 10.48550/ARXIV.2503.11609

Scientific Reports

Autori: Stockinger, Elisabeth; Gallotti, Riccardo; Hausladen, Carina Ines
Pubblicato in: Scientific Reports, 2024, ISSN 2045-2322
Editore: Scientific Reports
DOI: 10.3929/ETHZ-B-000692553

Federated Generalized Category Discovery

Autori: Pu, Nan; Li, Wenjing; Ji, Xingyuan; Qin, Yalan; Sebe, Nicu; Zhong, Zhun
Pubblicato in: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024, ISSN 2575-7075
Editore: IEEE
DOI: 10.5281/ZENODO.12627450

DeCLIP: Decoding CLIP Representations for Deepfake Localization

Autori: Smeu, Stefan; Oneata, Elisabeta; Oneață, Dan
Pubblicato in: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025, ISSN 2642-9381
Editore: IEEE
DOI: 10.48550/ARXIV.2409.08849

CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIP

Autori: Xing, Songlong; Zhao, Zhengyu; Sebe, Nicu
Pubblicato in: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025, ISSN 2575-7075
Editore: IEEE
DOI: 10.48550/ARXIV.2503.03613

Promptable Game Models: Text-guided Game Simulation via Masked Diffusion Models

Autori: Willi Menapace; Aliaksandr Siarohin; Stéphane Lathuilière; Panos Achlioptas; Vladislav Golyanik; Sergey Tulyakov; Elisa Ricci 0001
Pubblicato in: ACM Transactions on Graphics, 2024, ISSN 1557-7368
Editore: ACM Transactions on Graphics
DOI: 10.48550/ARXIV.2303.13472

Translating speech with just images

Autori: Oneață, Dan; Kamper, Herman
Pubblicato in: Interspeech 2024, 2024, ISSN 2958-1796
Editore: Interspeech 2024
DOI: 10.48550/ARXIV.2406.07133

P-TAME: Explain Any Image Classifier With Trained Perturbations

Autori: Mariano V. Ntrougkas; Vasileios Mezaris; Ioannis Patras
Pubblicato in: IEEE Open Journal of Signal Processing, 2025, ISSN 2644-1322
Editore: IEEE
DOI: 10.1109/OJSP.2025.3568756

Visually Grounded Few-Shot Word Learning in Low-Resource Settings

Autori: Leanne Nortje; Dan Oneata; Herman Kamper
Pubblicato in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2024, ISSN 2329-9304
Editore: IEEE
DOI: 10.48550/ARXIV.2306.11371

Cultivating Media Critical Thinking with a Socratic AI Coach: A Methodology

Autori: Panayiotis Kapetanakis, Ioannis Elissaios Paparigopoulos, Dora Katsamori, Eirini Papachristou, Georgios Petasis
Pubblicato in: International Journal of Research and Innovation in Social Science, Numero 9, 2025, ISSN 2454-6186
Editore: RSIS International
DOI: 10.47772/IJRISS.2025.910000678

Conference proceedings (36)

Conditioned Prompt-Optimization for Continual Deepfake Detection

Autori: Francesco Laiti; Benedetta Liberatori; Thomas De Min; Elisa Ricci 0001
Pubblicato in: Lecture Notes in Computer Science ISBN: 9783031781889, 2024
Editore: ICPR 2024
DOI: 10.48550/ARXIV.2407.21554

Disturbing Image Detection Using LMM-Elicited Emotion Embeddings

Autori: Tzelepi, Maria; Mezaris, Vasileios
Pubblicato in: 2024 IEEE International Conference on Image Processing Challenges and Workshops (ICIPCW), 2024
Editore: IEEE
DOI: 10.1109/ICIPCW64161.2024.10769133

[WACV 2026] AuViRe: Audio-visual Speech Representation Reconstruction for Deepfake Temporal Localization (with Model Checkpoints)

Autori: Koutlis, Christos; Papadopoulos, Symeon
Pubblicato in: WACVW 2026, 2025
Editore: IEEE
DOI: 10.5281/ZENODO.17698400

Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning

Autori: Thomas De Min; Massimiliano Mancini; Stéphane Lathuilière; Subhankar Roy; Elisa Ricci
Pubblicato in: CoRR, 2024, ISSN 1550-5790
Editore: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV),
DOI: 10.48550/ARXIV.2405.15633

Cross-modal Networks, Fine-Tuning, Data Augmentation and Dual Softmax Operation for MediaEval NewsImages 2023

Autori: A. Leventakis, D. Galanopoulos, V. Mezaris
Pubblicato in: CEUR Workshop Proceedings, 2024, ISSN 1613-0073
Editore: CEUR

Countering Misinformation via Emotional Response Generation

Autori: Russo, Daniel; Kaszefski-Yaschuk, Shane; Staiano, Jacopo; Guerini, Marco
Pubblicato in: EMNLP, 2023
Editore: ACL
DOI: 10.48550/arxiv.2311.10587

Cross-modal Image Recommendation for News Articles by Multimodal Foundation Models-based Retrieval-Reranking

Autori: Galanopoulos, Damianos; Goulas, Andreas; Mezaris, Vasileios
Pubblicato in: MediaEval 2025 Workshop, 2026
Editore: CEUR

When You Doubt, Abstain: A Study of Automated Fact-checking in Italian Under Domain Shift

Autori: Valer, Giovanni; Ramponi, Alan; Tonelli, Sara
Pubblicato in: CEUR Workshop Proceedings, ISSN 1613-0073
Editore: CEUR

The SpeeD–ZevoTech submission at DISPLACE 2023

Autori: Pîrlogeanu, Gabriel; Georgescu, Alexandru Lucian; Oneață, Dan; Cucu, Horia
Pubblicato in: INTERSPEECH 2023, ISSN 1990-9772
Editore: INTERSPEECH
DOI: 10.21437/INTERSPEECH.2023-1839

Variationist: Exploring Multifaceted Variation and Bias in Written Language Data

Autori: Ramponi, Alan; Casula, Camilla; Menini, Stefano
Pubblicato in: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), 2024
Editore: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
DOI: 10.5281/ZENODO.13785431

The Geography of Information Diffusion in Online Discourse on Europe and Migration

Autori: Elisa Leonardelli; Sara Tonelli
Pubblicato in: Proceedings of the International AAAI Conference on Web and Social Media, 2024
Editore: Proceedings of the International AAAI Conference on Web and Social Media,
DOI: 10.48550/ARXIV.2402.13800

Composite Data Augmentations for Synthetic Image Detection against Real-World Perturbations

Autori: Amarantidou, Efthymia; Koutlis, Christos; Papadopoulos, Symeon; Petrantonakis, Panagiotis
Pubblicato in: 2025
Editore: IEEE

Benchmarking the Generation of Fact Checking Explanations

Autori: Russo, Daniel; Tekiroğlu, Serra Sinem; Guerini, Marco
Pubblicato in: TACL, 2023, ISSN 2307-387X
Editore: ACL
DOI: 10.48550/arxiv.2308.15202

Frustratingly Easy Test-Time Adaptation of Vision-Language Models

Autori: Farina, Matteo; Franchi, Gianni; Iacca, Giovanni; Mancini, Massimiliano; Ricci, Elisa
Pubblicato in: Advances in Neural Information Processing Systems 37, 2024
Editore: Curran Associates, Inc.
DOI: 10.48550/ARXIV.2405.18330

The Phantom Menace: Unmasking Privacy Leakages in Vision-Language Models

Autori: Simone Caldarella; Massimiliano Mancini; Elisa Ricci 0001; Rahaf Aljundi
Pubblicato in: Lecture Notes in Computer Science ISBN: 9783031926471, 2025
Editore: ECCV 2024
DOI: 10.48550/ARXIV.2408.01228

EuroVerdict: A Multilingual Dataset for Verdict Generation Against Misinformation

Autori: Daniel Russo, Fariba Sadeghi, Stefano Menini, Marco Guerini
Pubblicato in: Findings of the Association for Computational Linguistics: ACL 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.FINDINGS-ACL.853

NullFace: Training-Free Localized Face Anonymization

Autori: Kung, H.-W., Varanka, T., Sim, T., & Sebe, N. (2026)
Pubblicato in: International Conference on Automatic Face and Gesture Recognition (FG)
Editore: International Conference on Automatic Face and Gesture Recognition (FG), 2026
DOI: 10.5281/ZENODO.19738917

HaSpeeDe3 at EVALITA 2023: Overview of the Political and Religious Hate Speech Detection task

Autori: Lai, Mirko; Celli, Fabio; Ramponi, Alan; Tonelli, Sara; Bosco, Cristina; Patti, Viviana
Pubblicato in: CEUR Workshop Proceedings, ISSN 1613-0073
Editore: CEUR

First-AID: the first Annotation Interface for grounded Dialogues

Autori: Stefano Menini, Daniel Russo, Alessio Palmero Aprosio, Marco Guerini
Pubblicato in: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.ACL-DEMO.54

Putting Context in Context: the Impact of Discussion Structure on Text Classification

Autori: Penzo, Nicolò; Longa, Antonio; Lepri, Bruno; Tonelli, Sara; Guerini, Marco
Pubblicato in: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 2024
Editore: Annual Meeting of the Association for Computational Linguistics (ACL)
DOI: 10.48550/ARXIV.2402.02975

MLLM Frame Subset Ensembling for Audio-Visual Video QA and MLLM-based Reranking for Ad-hoc Video Search in TRECVID 2025

Autori: Goulas, Andreas; Galanopoulos, Damianos; Patras, Ioannis; Mezaris, Vasileios
Pubblicato in: TRECVID 2025 Workshop, 2026
Editore: NIST
DOI: 10.5281/ZENODO.18346563

PAIR Diffusion: A Comprehensive Multimodal Object-Level Image Editor

Autori: Goel, Vidit; Peruzzo, Elia; Jiang, Yifan; Xu, Dejia; Xu, Xingqian; Sebe, Nicu; Darrell, Trevor; Shi, Humphrey
Pubblicato in: 2024
Editore: Zenodo
DOI: 10.5281/ZENODO.12636737

Retrieval-enriched zero-shot image classification in low-resource domains

Autori: Nicola Dall'Asen; Yiming Wang 0002; Enrico Fini; Elisa Ricci 0001
Pubblicato in: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024
Editore: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
DOI: 10.48550/ARXIV.2411.00988

Putting Context in Context: the Impact of Discussion Structure on Text Classification

Autori: Penzo, Nicolò; Longa, Antonio; Lepri, Bruno; Tonelli, Sara; Guerini, Marco
Pubblicato in: EACL Proceedings, ISSN 0736-587X
Editore: EACL

To Click It or Not to Click It: An Italian Dataset for Neutralising Clickbait Headlines.

Autori: Russo Daniel; Araque Oscar; Guerini Marco
Pubblicato in: 2024
Editore: CEUR Workshop Proceedings

An LLM Framework for Long-Form Video Retrieval and Audio-Visual Question Answering Using Qwen2/2.5

Autori: Galanopoulos, Damianos; Goulas, Andreas; Leventakis, Antonios; Patras, Ioannis; Mezaris, Vasileios
Pubblicato in: 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025
Editore: IEEE/CVF
DOI: 10.1109/CVPRW67362.2025.00358

Weakly-supervised deepfake localization in diffusion-generated images

Autori: Tantaru, Dragos; Oneata, Elisabeta; Oneata, Dan
Pubblicato in: WACV Proceedings, 2023, ISSN 1550-5790
Editore: IEEE
DOI: 10.1109/WACV57701.2024.00614

Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery

Autori: Haiyang Zheng; Nan Pu; Wenjing Li; Nicu Sebe; Zhun Zhong
Pubblicato in: Advances in Neural Information Processing Systems 37, 2024
Editore: Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI: 10.48550/ARXIV.2410.19213

VERGE in VBS 2026

Autori: Pantelidis, Nick; Kosmidou, Eleni; Galanopoulos, Damianos; Georgalis, Dimitriοs; Stefanos, Pasios; Apostolidis, Konstantinos; Goulas, Andreas; Pegia, Maria; Tsionkis, Georgios; Gkountakos, Konstantinos; Kouvrakis, Grigorios; Moumtzidou, Anastasia; Gialampoukidis, Ilias; Vrochidis, Stefanos; Mezaris, Vasileios; Kompatsiaris, Ioannis (Yiannis)
Pubblicato in: MMM 2026, 2026
Editore: Springer
DOI: 10.5281/ZENODO.18268841

Weighted Ensemble Models Are Strong Continual Learners

Autori: Imad Eddine Marouf; Subhankar Roy; Enzo Tartaglione; Stéphane Lathuilière
Pubblicato in: Lecture Notes in Computer Science - Computer Vision – ECCV 2024, 2024
Editore: ECCV 2024
DOI: 10.48550/ARXIV.2312.08977

Hierocles of Alexandria at Touché: Multi-task & Multi-head Custom Architecture with Transformer-based Models for Human Value Detection.

Autori: Legkas, S., Christodoulou, C., Zidianakis, M., Koutrintzes, D., Dagioglou, M., & Petasis, G.
Editore: Zenodo
DOI: 10.5281/ZENODO.19818946

Improving the Perturbation-Based Explanation of Deepfake Detectors Through the Use of Adversarially-Generated Samples

Autori: Konstantinos Tsigos; Evlampios Apostolidis; Vasileios Mezaris
Pubblicato in: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), 2025
Editore: IEEE/CVF
DOI: 10.5281/ZENODO.14995959

ITI-CERTH participation in ActEV and AVS Tracks of TRECVID 2024

Autori: Gkountakos, Konstantinos; Galanopoulos, Damianos; Leventakis, Antonios; Tsionkis, Georgios; Stavrothanasopoulos, Klearchos; Ioannidis, Konstantinos; Vrochidis, Stefanos; Mezaris, Vasileios; Kompatsiaris, Ioannis
Pubblicato in: TRECVID 2024 Workshop, 2025
Editore: NIST
DOI: 10.5281/ZENODO.14858855

VERGE in VBS 2025

Autori: Pantelidis, Nick; Georgalis, Dimitris; Pegia, Maria; Galanopoulos, Damianos; Apostolidis, Konstantinos; Stavrothanasopoulos, Klearchos; Moumtzidou, Anastasia; Gkountakos, Konstantinos; Gialampoukidis, Ilias; Vrochidis, Stefanos; Mezaris, Vasileios; Kompatsiaris, Ioannis (Yiannis)
Pubblicato in: Lecture Notes in Computer Science - MultiMedia Modeling, 2025
Editore: Springer
DOI: 10.5281/ZENODO.18324379

Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Era

Autori: Dan Oneata, Desmond Elliott, Stella Frank
Pubblicato in: Findings of the Association for Computational Linguistics: ACL 2025, 2025
Editore: Association for Computational Linguistics
DOI: 10.18653/V1/2025.FINDINGS-ACL.1240

Towards Quantitative Evaluation of Explainable AI Methods for Deepfake Detection

Autori: Konstantinos Tsigos; Evlampios Apostolidis; Spyridon Baxevanakis; Symeon Papadopoulos; Vasileios Mezaris
Pubblicato in: 3rd ACM International Workshop on Multimedia AI against Disinformation, 2024
Editore: ACM
DOI: 10.1145/3643491.3660292

Monographic books (1)

WavLM model ensemble for audio deepfake detection

Autori: Combei, David; Stan, Adriana; Oneață, Dan; Cucu, Horia
Pubblicato in: The Automatic Speaker Verification Spoofing Countermeasures Workshop (ASVspoof 2024), 2024
Editore: ASVspoof 2024
DOI: 10.48550/ARXIV.2408.07414

Other (1)

MCTD Policy Submission to the UK Joint Committee on National Security Strategy

Autori: Glenster, Ann Kristin ; Felsberger, Stefanie; Neff, Gina
Editore: Minderoo Centre for TEchnology and Democracy at the University of Cambridge MCTD