Countering Crime and Terrorism and their Links to Transnational Illegal Activities by Fostering International Cooperation

Projektinformationen

AVALANCHE

ID Finanzhilfevereinbarung: 101168393

DOI

10.3030/101168393

EK-Unterschriftsdatum 19 Juli 2024

Startdatum 1 Oktober 2024

Enddatum 30 September 2026

Finanziert unter

• Civil Security for Society

Gesamtkosten

Keine Daten

EU-Beitrag

€ 1 499 800,00

Koordiniert durch

UBITECH LIMITED
Cyprus

Periodic Reporting for period 1 - AVALANCHE (Countering Crime and Terrorism and their Links to Transnational Illegal Activities by Fostering International Cooperation)

Berichtszeitraum: 2024-10-01 bis 2025-09-30

Zusammenfassung vom Kontext und den Gesamtzielen des Projekts

AVALANCHE addresses the growing challenge faced by law enforcement agencies (LEAs) in analysing large volumes of online information related to disinformation, hate speech, deepfakes and other harmful content circulating across the surface and dark web. Current investigative processes are hindered by fragmented tools, limited automation and difficulties in understanding how harmful content propagates across platforms. Additionally, LEAs need improved mechanisms to securely exchange information and evidence across systems and jurisdictions.

The project’s overall objective is to co-develop with LEAs a set of AI-supported solutions that improve the detection, investigation and analysis of complex online content. This includes tools for web crawling, behavioural analysis, sentiment and hate-speech detection, deepfake identification, and secure information exchange. Social sciences and humanities contribute by helping shape realistic user requirements, operational workflows and ethical safeguards. Throughout the project, Ethical-by-Design, Privacy-by-Design and compliance with GDPR and the Law Enforcement Directive guide development to ensure trustworthy and responsible use.

The expected impact is to enhance situational awareness, provide more efficient investigative capabilities and enable harmonised information exchange, supporting LEAs in addressing online criminal and harmful information activities.

Arbeit, die ab Beginn des Projekts bis zum Ende des durch den Bericht erfassten Berichtszeitraums geleistet wurde, und die wichtigsten bis dahin erzielten Ergebnisse

During the first reporting period, AVALANCHE established its analytical, technical and ethical foundations. A complete State-of-the-Art and gap analysis was conducted, followed by structured requirements elicitation through questionnaires and interviews with the end-user (SPP). These inputs were consolidated into validated scenarios, KPIs and system requirements.

Based on these results, the consortium produced the AVALANCHE Reference Architecture, describing system components, data flows, actors, interaction diagrams and integration points aligned with LEA workflows.

Technical progress advanced in four key areas:
Web data collection: A first version of the MEDUSA crawler was released, capable of collecting textual and multimedia content from surface and dark web sources. A configurable forum parser and an initial disinformation detection prototype were also developed.
Behavioural analysis: The foundation for identifying the “origin of spread” of online content was defined. A dedicated OCR tool for extracting text from images was implemented, with planned extension to video. Deepfake detection models were benchmarked.
Sentiment and hate-speech detection: Benchmarking of BERT-based, local LLM and commercial LLM approaches led to a decision to develop an in-house NLP solution aligned with LEA requirements.
Secure information exchange: Initial work on a federated data schema and a secure, encrypted exchange mechanism was completed, including concepts for hashing, signing, integrity verification and one-time retrieval links.

Legal, ethical and data governance work progressed through the establishment of the Ethical Advisory Board and the preparation of a FAIR-aligned Data Management Plan, ensuring compliance with data protection and ethical requirements.

Fortschritte, die über den aktuellen Stand der Technik hinausgehen und voraussichtliche potenzielle Auswirkungen (einschließlich der bis dato erzielten sozioökonomischen Auswirkungen und weiter gefassten gesellschaftlichen Auswirkungen des Projekts)

AVALANCHE advances capabilities in several areas compared to existing tools. The MEDUSA crawler introduces adaptable collection features that support diverse online sources, including dark web forums. The behavioural analysis component provides a structured methodology for identifying the origin and propagation patterns of online content. A dedicated OCR tool was created to address specific user needs for processing images and the benchmarking of deepfake detection approaches supports the integration of reliable models within the system.

The sentiment and hate-speech detection work contributes by defining an explainable, multi-label approach tailored to investigative needs while avoiding reliance on external services. The secure information-exchange concept introduces integrity-preserving, encrypted mechanisms aligned with the project’s technical architecture.

Further uptake will depend on continued development, integration of all modules, expanded datasets for model training, and validation during pilots in real operational environments.

AVALANCHE project logo

AVALANCHE website screenshot

AVALANCHE 1st hackathon

AVALANCHE plenary meeting in Dublin

AVALANCHE participation in Projects to Policy Seminar