VIGILANT: Vital IntelliGence to Investigate ILlegAl DisiNformaTion
VIGILANT is a Horizon Europe project aimed at application of data collection and AI-based web content analysis methods to support police authorities in investigations of disinformation-related crime. In this project, KInIT collaborates with research institutions, software companies, police authorities and training institutions from across Europe.
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, as well ongoing Horizon Europe 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 formats (text, image, video) and in multiple languages. It is also suitable for investigating hate speech, violent nationalist or separatist movements, radicalisation, extremist groups, incels, lone 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 five European PAs.
KInIT’s role in the project focuses on efficient content sourcing, preprocessing and automated disinformation detection. We will also contribute to the overall ethical framework for using technology in disinformation-related criminal investigations.
VIGILANT’s overall objective is to provide a comprehensive framework and methodology that:
1) integrates the latest developments in tools tailored to analyse, detect, mitigate and prevent disinformation with implications for security, guided by ethical and social aspects;
2) implements best practices in data acquisition, processing and storage, compliant with GDPR and the legal requirements for police investigations and;
3) equips Officers with training and knowledge about disinformation campaigns and the appropriate actions for dealing with them.
VIGILANT aims to fulfill its objectives through:
- Textual tools for disinformation analysis. VIGILANT will develop natural language processing tools for disinformation analysis and detection in multiple languages, with a focus on high precision outputs, avoiding model biases.
- Image and video forensics. VIGILANT will develop video and image processing tools for disinformation analysis and forensics, including object detection and person of interest identification, following stringent ethics protocols.
- Network analysis tools. VIGILANT will provide network analysis tools for the identification of organised disinformation campaigns. These will further identify the main actors in these campaigns, focusing on the targets of disinformation.
- Impact and intervention approaches. VIGILANT will develop a tool for analysing the impact of disinformation campaigns on citizens and the society. Also, tools for supporting Officers with countering disinformation campaigns will be provided. Thanks to this, PAs will be able to source information useful for inoculating against disinformation based on societal information and informing the intervention approaches with the most chance of success.
- Universal and interoperable data model/protocol. VIGILANT will deliver an automated data collection pipeline, capable of extracting publicly available data from news media, social media platforms and other online sources (while adhering to ethical principles and data providers’ T&C). Besides automated data collection, VIGILANT will allow PAs to easily input their own data. All data will be stored for the necessary period only; GDPR and relevant law enforcement legislation will be observed. The data will be effectively scrutable through robust search functionality (including semantic searching).
- Customizable and interactive dashboard. VIGILANT will develop a Dashboard – a fully customisable interface which enables the Officers to view and interact with the disinformation for their investigations. To achieve the highest possible usability and value for PAs, a co-creation and co-design-based protocol for requirements gathering, enabling a user-centric approach to tools development, will be introduced.
- Training, training materials and manual for defending against manipulation tactics. The VIGILANT project will also deliver training for Officers on using the platform and on disinformation in general. Long term sustainability is also built into the project. We will set up a sustainable support network based on the training of European Officers tasked with combating disinformation. The training materials will be designed by PA specialists with the broad purpose of not only instructing Officers on how to use VIGILANT, but also providing a framework of actions to be taken when dealing with disinformation.
Vigilant will enable human law enforcement analysts to be more efficient, while retaining the ethical and legal boundaries pertaining to the delicate domain of disinformation crime investigation. This is especially important in the context of Slovakia, where trust in public authorities needs to be improved.
Jakub Šimko, Senior researcher
Kempelen Institute of Intelligent Technologies
Ethics and Law Specialist
This project is funded by the European union.