In 2015-2016, 20+ terrorist attacks occurred in EU28, all of them carried out by individuals radicalized by terrorist propaganda. Recruitment of this new breed of terrorists was done via social media and the Internet. To prevent such events from happening in the future and fight radicalization, it is crucial to detect cyberpropaganda early. However, social media providers (e.g. Twitter) admit that at the moment there is no adequate tool to identify terrorist-related content on the Internet. As the result, they are forced to rely on proprietary spam-fighting tools, user reports and human analysis to track down radicalized accounts that promote terrorism. Insikt Intelligence is a Spanish SME led by the EYIF 2016 Female Web Entrepreneur finalist that developed INSIKT, a novel social data mining platform to detect & defeat violent online radicalization. An early version of INSIKT was validated by several EU law enforcement agencies (LEAs), approved and attracted commercial interest. This Phase 2 project will trial INSIKT at 4 European LEAs that are looking for effective tools to prevent radical messages from spreading and reaching people vulnerable to radicalization. INSIKT provides a novel solution for LEA analysts to detect terrorist propaganda on all social media: it identifies radical content, suspicious messages and covert radicalization process with the help of sophisticated text mining algorithms. INSIKT relies on deep learning to develop automatically new models which can be used to detect other criminal activity as well. INSIKT is fit to become an important new tool in LEAs’ investigation and evidence gathering arsenal, giving them highly accurate, multilingual and real-time detection capabilities. This project will allow us to improve INSIKT, integrate it with existing LEA tools and commercialize it, addressing the needs of the €60+B security market, with the effect of creating 50+ jobs and €11.7M annual revenue within 5 years from market launch.

An interconnected city grid of sensors, such as of cameras or environmental sensors, offers a wealth of actionable Big Data. In addition to better managing traffic and public transit, as well as controlling pollution, they can be used for enhanced policing, crowd control, and even public sentiment monitoring. However, such smart systems increase the risk of unethical use of personal data, and increase the attack surface of a city as multiple interconnected IT systems control key infrastructures such as transport, energy, water distribution, etc. To address the growing security and ethical threats on smart cities, the project will develop an integrated toolkit that covers the complete physical and cybersecurity value chain (detection, simulation & analysis, intervention). The project will enhance the resilience of cities in the face of security events in public spaces, by addressing three main aspects of urban security in smart cities: • Technologies: integrating and developing the tools and processes underlying the capacity of cities to manage both physical security and cyber security, leveraging the power of IoT, Artificial Intelligence and Big Data analysis • Ethics: ensuring smart city capabilities are developed for the benefit of society, balancing potentially conflicting needs to collect, transform and share large amounts of data with the protection of data privacy • Processes: delivering a multi-tenant solution fully aligned with the operational needs of multiple city stakeholders (e.g. police, first responders, municipalities) supported by a framework gathering deployment guidelines and best practices The consortium includes 17 partners from 11 different EU Member States and Associated Countries, including 2 local government authorities (City of Padova and City of Oslo) that will lead the field trial implementations. The project will also be supported by a Community of Safe and Secure Cities (COSSEC) gathering other cities to provide feedback.

The RED-Alert project will bring data mining and predictive analytics tools to the next level, developing novel natural language processing (NLP), semantic media analysis (SMA), social network analysis (SNA), Complex Event Processing (CEP) and artificial intelligence (AI) technologies. These technologies will be combined for the first time and validated by 6 law enforcement agencies (LEAs) to collect, process, visualize and store online data related to terrorist groups, allowing them to take coordinated action in real-time while preserving the privacy of citizens. The RED-Alert solution will outperform state-of-the-art solutions in terms of number of languages supported, privacy-preserving capabilities, usability, detection performance, real-time capabilities and integration capabilities. The RED-Alert approach combines for the first time the CEP methodology with NLP/SMA and SNA applications in the context of social media data analytics, transforming (unstructured) social media data into (structured) events enhanced by semantic attributes. For example, a tweet will be an event consisting of content (expressed as NLP features e.g. concepts, sentiment, entities, etc.) and context (time and the author including SNA features e.g. number of followers, number of links, etc.). Turning unstructured social media data into structured events is key, as it allows the system to use (event) rules (event temporal logic, event logic patterns, even counting, absence of events) to infer insights or create alerts in real-time. The project impact is supported by the participation of Europol and specific dissemination activities around the World Counter-Terrorism Summit, organized by one of the partners. The total requested EC funding is 5M Euros and the project duration 36 months.

In order to support the fight against radicalization and thus prevent future terrorist attacks from taking place, the CounteR project will bring data from disperse sources into an analysis and early alert platform for data mining and prediction of critical areas (e.g. communities), aiming to be a frontline community policing tool which looks at the community and its related risk factors rather than targeting and surveilling individuals. This is a key point in ensuring the privacy of citizens and the protection of their personal data, an issue that has been of great concern to policymakers and LEAs alike, who must balance the important work they do with the need to protect innocent individuals. The system will incorporate state of the art NLP technologies combined with expert knowledge into the psychology of radicalization processes to provide a complete solution for LEAs to understand the when, where and why of radicalization in the community to help combat propaganda, fundraising, recruitment and mobilization, networking, information sharing, planning/coordination, data manipulation and misinformation. Information gained by the system will also allow LEAs and other community stakeholders to implement prevention programs and employ counternarratives rather than relying solely on surveillance. The CounteR solution will cover a wide range of information sources, both dynamic (e.g. social media) and offline (e.g. open data sources) and combined with world-renowned expertise in radicalization processes and their psychology. The CounteR solution will allow LEAs to take coordinated action in real-time while also preserving the privacy of citizens, as the system will target “hotspots” of radicalization rather than individuals. In addition, the CounteR solution will support information sharing between European LEAs and foster collaboration between diverse agencies by providing an open platform which prioritizes harmonized information formats.