Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Norway

Research and Innovation Action · Running

DEFORM Deepfake detection and Explainability using FOundation Representation Models

Coordinator
Norges Teknisk-Naturvitenskapelige Universitet NTNU, Norway
Runs
1 September 2026 to 31 August 2029
Status
Running
EU funding
€3.0m
Total cost
€3.0m
Partners
14 organisations in 6 countries
Type
Research and Innovation Action
Grant agreement
101308502

What the project is doing

In the project's own words, from its summary on CORDIS.

DEFORM addresses the urgent need for robust, explainable AI forensic tools to counter the growing threat of Deepfakes, AI-generated or manipulated audio, video, and images that challenge current forensic tools. The project will deliver a modular, practitioner-driven AI framework with multi-level explainability for multimodal Deepfake detection and source tracing, validated (TRL5) and demonstrated (TRL6) in 2 operational forensic environments.

DEFORM’s innovative approach leverages emerging Foundation Representation Models and few-shot learning for robust and multi-level explainable AI (xAI) to ensure adaptability to new manipulation techniques and transparency for diverse stakeholders, including investigators, forensic examiners, legal professionals, and lay audiences. The consortium unites leading scientific, technical, legal, and practitioner partners from six European countries, including police authorities and forensic institutes, to co-design, validate, and demonstrate solutions aligned with EU legal, ethical, and forensic standards.

By twinning expert research partners in scientific, legal and ethical part from partner countries with practitioners from respective countries, DEFORM outputs include validated detection and source tracing modules for image, audio, and video; human-centred xAI explanations; annotated Deepfake datasets; and open-source forensic tools for wide adoption. DEFORM’s impact pathway ensures improved reliability and usability for modern forensic analysis using new and emerging technology.

This will enhance the capacity for law enforcement to fight against crimes in digital area and strengthen public trust. DEFORM's innovative training curricula will bridge the gap between research and operational practice. Also, stakeholder engagement will foster wide adoption and contribute to a strong and independent EU AI continent.

Topics

Who is involved

OrganisationCityCountryRole
Norges Teknisk-Naturvitenskapelige Universitet NTNUTrondheimNorwayCoordinator
Els Kindt BvbaMeiseBelgiumParticipant
Vrije Universiteit BrusselBruxelles / BrusselBelgiumParticipant
Fondation De L'institut De Recherche IdiapMartignySwitzerlandParticipant
Eurecom GieBiotFranceParticipant
IDEMIA Public Security FranceCourbevoieFranceParticipant
Ministere De L'interieurParisFranceParticipant
Ministero Dell'internoRomaItalyParticipant
Universita Degli Studi Di CataniaCataniaItalyParticipant
European Association for BiometricsAmsterdamNetherlandsParticipant
Jasserand Breeman Catherine AgnesAmsterdamNetherlandsParticipant
Netherlands Forensic InstituteThe HagueNetherlandsParticipant
Universiteit TwenteEnschedeNetherlandsParticipant
PolitidirektoratetOsloNorwayParticipant

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI