Periodic Reporting for period 1 - PREVISION (Prediction and Visual Intelligence for Security Information)
Reporting period: 2019-09-01 to 2020-08-31
a) worked towards delivering a set of the first versions of all data streams analytics tools. In particular, crawling tools have been developed for extreme-scale data collection, while for the processing of the heterogeneous data sources the developed tools include tools for performing visual and textual analysis, as well as tools for analysing social networks.
b) more than 50 biographies of known terrorists and extremists were collected in order to gain basic knowledge about their behavior and develop the corresponding analysis models for the detection and modification of radicalization processes.
c) own taxonomies and keywords had to be developed and created that are necessary to analyze corresponding findings from texts, voice and video files and to be able to feed them into a scoring system.
d) trend and network analyses will be applied in the areas of cybercrime and organized crime. This will make it possible to identify and analyze networks of relationships between natural persons, legal entities and companies/organizations on the basis of personal or public data.
e) a list of tools was identified, that potentially constitute competition for PREVISION situational awareness applications.
f) the infrastructure for installing the PREVISION platform has been configured and the first architectural version of the platform was defined.
g) simulated/synthetic data for testing has been prepared and testing was performed for routing and processing of simulated data.
h) ensuring compliance with the relevant ethical and legal standards. Ethical and legal guidelines for the development and use of tools. An Ethics Review Panel has been formed that consists of six experts (three external and three internal to the consortium) and provides advice on ethical and fundamental rights issues that occur in the project.
Regarding steganographic traffic detection, PREVISION will process network traffic traces with and without covert traffic in conjunction with information that such traces contain (or not) secret data.
With respect to information fusion, PREVISION addressed three main challenges using Markov logic networks, the data association problem, the need for a high quality statistical model, which must be trained using sufficient labelled training data, and the adaptation of the logical (object oriented) model during its usage.
PREVISION also develops a toolkit to identify radicalization tendencies in society at an early stage and, based on this, to develop risk forecasts that will allow security authorities in advance to take preventive action. This requires a continuous observation of social processes and especially of violent political milieus.
PREVISION establishes an open and future-proof platform for providing cutting-edge practical support to LEAs and practitioners in the fight against terrorism, organised crime and cybercrime, creating a number of impacts on societal and innovation aspects, such as:
1. Contribution to the Security Union.
2. Innovation capacity and integration of new knowledge.
3. Strengthening the competitiveness and growth of companies.
4. Societal impact(s), including alleviation of first/second/third order victimisation and reduction of financial costs (estimated at an astonishing $600 billion in 2017).