Vital IntelliGence to Investigate ILlegAl DisiNformaTion

Civil SecurityHORIZON-IAID: 101073921
EC Contribution
€33,766
Consortium Size
19 orgs
Start Year
2022
Summary

Identifying, tracking and investigating online disinformation and other problematic content is an extremely complex problem. Many (European) Police Authorities (PAs) do not have access to any specialised tools or technologies to help them combat disinformation. Some of the better equipped PAs are using unsuitable off-the-shelf products that were designed to enable commercial companies to monitor social media chatter about their brands and products or to track the success of advertising campaigns. Such products are not capable of dealing with the complexities of disinformation nor do they provide advanced analysis tools and technologies tailored to the PAs needs. The VIGILANT project solves this problem. It is an integrated platform of advanced disinformation identification and analysis tools and technologies employing state-of-the-art AI methods which were developed as part of several highly successful FP7 and H2020 projects. They will be tailored to PAs use cases and needs, following an ethical-by-design and user-centric approach. In addition, social and behavioural aspects are also taken into account when designing tools and presenting results. VIGILANT covers disinformation from all major sources (e.g., major social media platforms, fake news websites), in all modalities (text, image, video) and in multiple languages. It is also suitable for investigating hate speech, violent nationalist or separatist movements, radicalisation, extremist groups, incels, loan wolfs, and other counter terrorism threats. The project also provides innovative solutions to leverage the knowledge and experience of other stakeholder organisations and (social) media companies. Finally, the project includes training for PAs in the use of VIGILANT and in conducting disinformation investigations as part of a long term sustainable training network. The interdisciplinary consortium includes expertise from social sciences and humanities, ethics, computer science commercial and four European PAs.

Consortium (19)

Project Results (38)

Source: CORDIS, the EU research results database.

Publications (23)
GateNLP at SemEval-2025 Task 10: Hierarchical Three-Step Prompting for Multilingual Narrative Classification
· 2025
Iknoor Singh, Carolina Scarton, Kalina Bontcheva
It’s All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMs
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing· 2025DOI
Yue Li, Zhixue Zhao, Carolina Scarton
Label Set Optimization via Activation Distribution Kurtosis for Zero-Shot Classification with Generative Models
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing· 2025DOI
Yue Li, Zhixue Zhao, Carolina Scarton
MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media Texts
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)· 2025DOI
Dominik Macko, Jakub Kopál, Robert Moro, Ivan Srba
The disinformation lifecycle: an integrated understanding of its creation, spread and effects
Discover Global Society· 2025DOI
Kimberley Kruijver, Neill Bo Finlayson, Beatrice Cadet, Sico van der Meer
UKElectionNarratives: A Dataset of Misleading Narratives Surrounding Recent UK General Elections
· 2025DOI
Jisun An, Yu-Ru Lin, Yelena Mejova, Eni Mustafaraj, Juhi Kulshrestha, Ingmar Weber
A Ship of Theseus: Curious Cases of Paraphrasing in LLM-Generated Texts
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)· 2024DOI
Nafis Irtiza Tripto, Saranya Venkatraman, Dominik Macko, Robert Moro, Ivan Srba, Adaku Uchendu, Thai Le, Dongwon Lee
Are Publicly Available (Personal) Data 'Up for Grabs' ? A Discussion of Three Privacy Arguments
SSRN Electronic Journal· 2024DOI
Elisa Orrù
Authorship Obfuscation in Multilingual Machine-Generated Text Detection
Findings of the Association for Computational Linguistics: EMNLP 2024· 2024DOI
Dominik Macko, Robert Moro, Adaku Uchendu, Ivan Srba, Jason S Lucas, Michiharu Yamashita, Nafis Irtiza Tripto, Dongwon Lee, Jakub Simko, Maria Bielikova
Comparison between parameter-efficient techniques and full fine-tuning: A case study on multilingual news article classification
PLOS ONE· 2024DOI
Razuvayevskaya, Olesya; Wu, Ben; Leite, João A.; Heppell, Freddy; Srba, Ivan; Scarton, Carolina; Bontcheva, Kalina; Song, Xingyi
Disinformation Capabilities of Large Language Models
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)· 2024DOI
Ivan Vykopal, Matúš Pikuliak, Ivan Srba, Robert Moro, Dominik Macko, Maria Bielikova
Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)· 2024DOI
Jan Cegin, Branislav Pecher, Jakub Simko, Ivan Srba, Maria Bielikova, Peter Brusilovsky
Fighting Randomness with Randomness: Mitigating Optimisation Instability of Fine-Tuning using Delayed Ensemble and Noisy Interpolation
Findings of the Association for Computational Linguistics: EMNLP 2024· 2024DOI
Branislav Pecher, Jan Cegin, Robert Belanec, Jakub Simko, Ivan Srba, Maria Bielikova
IMGTB: A Framework for Machine-Generated Text Detection Benchmarking
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)· 2024DOI
Michal Spiegel, Dominik Macko
KInIT at SemEval-2024 Task 8: Fine-tuned LLMs for Multilingual Machine-Generated Text Detection
Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)· 2024DOI
Michal Spiegel, Dominik Macko
A Large-Scale Comparative Study of Accurate COVID-19 Information versus Misinformation
· 2023DOI
Mu, Yida; Jiang, Ye; Heppell, Freddy; Singh, Iknoor; Scarton, Carolina; Bontcheva, Kalina; Song, Xingyi
Analysing State-Backed Propaganda Websites: a New Dataset and Linguistic Study
· 2023DOI
Heppell, Freddy; Bontcheva, Kalina; Scarton, Carolina
Does Explanation Matter? An Exploratory Study on the Effects of Covid 19 Misinformation Warning Flags on Social Media
· 2023DOI
Barman, Dipto; Conlan, Owen
KInITVeraAI at SemEval-2023 Task 3: Simple yet Powerful Multilingual Fine-Tuning for Persuasion Techniques Detection
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)· 2023DOI
Hromadka, Timo; Smolen, Timotej; Remis, Tomas; Pecher, Branislav; Srba, Ivan
MULTITuDE: Large-Scale Multilingual Machine-Generated Text Detection Benchmark
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing· 2023DOI
Macko, Dominik; Moro, Robert; Uchendu, Adaku; Lucas, Jason Samuel; Yamashita, Michiharu; Pikuliak, Matúš; Srba, Ivan; Le, Thai; Lee, Dongwon; Simko, Jakub; Bielikova, Maria
NEXT: An Event Schema Extension Approach for Closed-Domain Event Extraction Models
· 2023DOI
Elena Tuparova, Petar Ivanov, Andrey Tagarev, Svetla Boytcheva, Ivan Koychev
SheffieldVeraAI at SemEval-2023 Task 3: Mono and Multilingual Approaches for News Genre, Topic and Persuasion Technique Classification
· 2023DOI
Wu, Ben; Razuvayevskaya, Olesya; Heppell, Freddy; Leite, João A.; Scarton, Carolina; Bontcheva, Kalina; Song, Xingyi
Multilinguality in the VIGILANT project
Carolina Scarton, Charlotte Prescott, Chris Bayliss, Chris Oakley, Joanna Wright, Stuart Wrigley, Xingyi Song, Edward Gow-Smith, Mikel Forcada, Helena Moniz
Deliverables (15)
Data Management Plan
Data Management Plan
Data Management Plan
Documents, reports
Documents, reports
Documents, reports
Documents, reports
Documents, reports
Documents, reports
Documents, reports
Documents, reports
Documents, reports