Skip to main content

Analysis System for Gathered Raw Data

Periodic Reporting for period 3 - ASGARD (Analysis System for Gathered Raw Data)

Reporting period: 2019-09-01 to 2020-11-30

ASGARD has a singular goal, contribute to Law Enforcement Agencies Technological Autonomy and effective use of technology. Technologies will be transferred to end users under an open source scheme focusing on Forensics, Intelligence and Foresight (Intelligence led prevention and anticipation).

ASGARD will drive progress in the processing of seized data, availability of massive amounts of data and big data solutions in an ever more connected world. New areas of research will also be addressed.

The consortium is configured with LEA end users and practitioners “pulling” from the Research and Development community who will “push” transfer of knowledge and innovation.

A Community of LEA users is the end point of ASGARD with the technology as a focal point for cooperation (a restricted open source community).

In addition to traditional Use Cases and trials, in keeping with open source concepts and continuous integration approaches, ASGARD will use Hackathons to demonstrate its results. Vendor lock-in is addressed whilst also recognising their role and existing investment by LEAs. The project will follow a cyclical approach for early results. Data Set, Data Analytics (multimodal/multimedia), Data Mining and Visual Analytics are included in the work plan. Technologies will be built under the maxim of “It works” over “It’s the best”. Rapid adoption/flexible deployment strategies are included.

The project includes a licensing and IPR approach coherent with LEA realities and Ethical needs. ASGARD includes a comprehensive approach to Privacy, Ethics, Societal Impact respecting fundamental rights. ASGARD leverages existing trust relationship between LEAs and the research and development industry, and experiential knowledge in FCT research. ASGARD will allow its community of users leverage the benefits of agile methodologies, technology trends and open source approaches that are currently exploited by the general ICT sector and Organised Crime and Terrorist organisations.
During the initial reporting period, the project completed most of the end-user (LEA) definition and priorisation of use-cases, user-stories, end-user requirements, the overall technical architecture and the initial set of system specifications of the tools. The requirements, system specifications, and system architecture are revisited and updated if needed after each of the 6 full-development cycles scheduled for the project. During the initial period pre-existing background technologies were adapted to comply with the agreed ASGARD interfaces.

During the second period (months 19 to 36), three full-development cycles have been completed and presented/evaluated by the consortium at three "hackathon" events (months 21, 27, and 33). During this period, the effort has been focused on development and delivery of new tools or of wrappers or enhancements to pre-existing tools. In total, around 50 tools were delivered. Not all tools are equally mature, some are at their early stages of development/maturity and some others are quite mature. During the 4th hackathon, it was identified the need to report the maturity of the tools being delivered, thus a task-force was launched to design and implement a tool maturity evaluation model, process, and tool. The Alpha version of the model and of the tool has been mainly developed during this second period and it will be delivered on the 6th hackathon event (which is part of the next reporting period).

Also during this period, relevant stakeholders were proactively reached, inviting them to join the Stakeholder Advisory Group (SAG) and also to attend our hackathon events. By the end of the second period, the SAG of the project includes 5 members in the Strategic Group (EUROPOL, ENLETS, ENFSI, PSCE, INTERPOL), 24 members in the Operational Group (EFSI, EE Police, HP, IGPR, PMM, GARDA, OKOKRIM, PSNI, BW police, BKA, SW Police, Zürich police, ERTZ, AT DEF, INTERPOL (Lyon), EC3, ECTC, INCIBE, ZITIS, San Sebastian Police, Spanish National Police, Gendarmerie, Slovenian Police), 4 members of the Industry Group (Telefónica, BT, Eurocrime, NEC), and 13 members of the Research and Academia Group (FREETOOLS, TENSOR, I-LEAD, ILEANet, Vox-Pol, DANTE, TAKEDOWN; RAMSES and FORENSOR projects, CEPOL, ASA, CERIDES, JRC, L3CE). In total: 46 organisations represented in the SAG from more than 15 countries.

Moreover, during the second period, the content management process (including the social, ethical, legal, and privacy assessment) was refined and implemented. There is a dataset registry that by the end of the second period had 186 datasets from different sources covering a wide range of use cases, including dataset ID, SELP Unit approval status (97 SELP approved), availability for ASGARD (172 available), name, source, use case and description established.
During the project, a new and more efficient way of collaboration between LEA, Research Technology Organisation (RTO) and Industry has been developed. The long-lasting and sustainable community that ASGARD aims to build should deliver on regular basis technological tools and solutions to LEAs to help them increase their technological autonomy to fight better crime and terrorism. Foresight, intelligence, and forensic domains are the main focus. The range of tools allow gathering, processing, and analysing large amounts of (big) data in order to extracting knowledge from multiple heterogeneous sources and data types (text, audio, image, video, digital-forensics).

In short, the essense of the new and more efficient way of collaboration consist in adopting and adapting to the needs of EU collaborative research projects many of the principles and best practices of Open Source Model (e.g. open collaboration, decentralisation, peer-production, and iterative and incremental full-development cycles. The full development, integration, and testing cycles last 6 months. At the end of each of these cycles the tools that have passed the tests are released and jointly evaluated at "hackathon" type of events. Partner LEA can then install in their own premises the released tools and conduct their own evaluations (with their own data). The lessons learnt extracted during the "hackathon/CtF" events and the feedback provided by the post-hackathon/CtF LEAs evaluations allow adjusting and refining the requirements and the development plan of the subsequent cycles. Starting since the 4th "hackathon", Capture-the-Flag (CtF) type of exercises were also conducted. The CtF exercises have proven to be a better way of presenting and evaluating the tools than the originally planned "hackathon" events.

In addition, the Tool Maturity Evaluation Model (and the TRL Calculator tool developed as part of it) proposes a new multidimensional approach to evaluate the maturity of the tools delivered by ASGARD that could easily be extended to other projects. For each of the dimensions (i.e. Requirements and functionality, Documentation, Operation and Maintenance, End-user testing/feedback, Security, and Legal, Ethical & Privacy), a set of indicators per level have been identified. The idea is that a pool of experts in each of the dimensions evaluates the tools against the indicators. More details about this can be found in WP4 progress report.

Besides, at a more granular level, several tools have published papers on conferences and journals describing the work done beyond state of the art (see Publications section).
Diagram describing the ASGARD methodology
Hackathon written with Scrabble pieces and the ASGARD logo
ASGARD Consortium map