Periodic Reporting for period 1 - GRACE (Global Response Against Child Exploitation)
Reporting period: 2020-06-01 to 2021-11-30
The growth in online child sexual exploitation and abuse (CSEAM) material is a significant challenge for European law enforcement agencies(LEA). Referrals of CSEAM exceed the capacity of LEAs to respond in a practical and timely manner. To safeguard victims, prosecute offenders and limit the spread of CSEAM, LEAs need a next-generation AI-powered investigative platform.
The sexual exploitation and abuse of children, the production of CSEM and subsequent distribution of this material via the internet is a shocking crime. Referrals from Online Service Providers (OSPs) are crucial to fighting CSEA. Growth in the number of referrals of CSEAM to LEAs is driven both by increased availability and distribution of online CSEAM and improved detection and reporting processes. The extent of referrals is affecting LEAs' capacity to respond promptly, leading to an inability to prevent harm to infants and children, rescue those in immediate danger, and investigate and prosecute perpetrators. Recent improvements to the referral process have improved LEAs capabilities. However, the sheer volume of data obtained in CSEA cases stretches human resources, the limits of manual analysis beyond most LEAs reach.
GRACE aims to equip European law enforcement agencies with advanced analytical and investigative capabilities to respond to the spread of online child sexual exploitation material. At the heart of the project, GRACE has three core concepts.
1- Address the volume and analyse the content of online CSEAM through technological innovations;
2.- Provide genuine operational value to LEAs in their investigation of online CSEAM; and
3.- Impact at the strategic and policy level in the harmonisation of EU-wide responses to CSEA.
GRACE will apply proven techniques in Machine Learning to the referral and analysis process while embracing the technical, ethical and legal challenges unique to fighting CSEA. GRACE will leverage resources already in place at Europol and the nine European Union Member State LEAs within the consortium. The goal for GRACE is to attempt to provide results early, frequently and flexibly, prioritising easy wins in the research plan (e.g. deduplication).
Unique to GRACE is the development and application of a Federated Learning approach to the challenge of optimising analysis and information flow in a privacy-aware and security-sensitive manner. GRACE will enable cooperation between LEAs in improving their capabilities while harnessing their experiential knowledge.
The results of GRACE will be available to Europol and the Member State LEAs for unrestricted use in their operations, helping to ensure their future technological autonomy.
The sexual exploitation and abuse of children, the production of CSEM and subsequent distribution of this material via the internet is a shocking crime. Referrals from Online Service Providers (OSPs) are crucial to fighting CSEA. Growth in the number of referrals of CSEAM to LEAs is driven both by increased availability and distribution of online CSEAM and improved detection and reporting processes. The extent of referrals is affecting LEAs' capacity to respond promptly, leading to an inability to prevent harm to infants and children, rescue those in immediate danger, and investigate and prosecute perpetrators. Recent improvements to the referral process have improved LEAs capabilities. However, the sheer volume of data obtained in CSEA cases stretches human resources, the limits of manual analysis beyond most LEAs reach.
GRACE aims to equip European law enforcement agencies with advanced analytical and investigative capabilities to respond to the spread of online child sexual exploitation material. At the heart of the project, GRACE has three core concepts.
1- Address the volume and analyse the content of online CSEAM through technological innovations;
2.- Provide genuine operational value to LEAs in their investigation of online CSEAM; and
3.- Impact at the strategic and policy level in the harmonisation of EU-wide responses to CSEA.
GRACE will apply proven techniques in Machine Learning to the referral and analysis process while embracing the technical, ethical and legal challenges unique to fighting CSEA. GRACE will leverage resources already in place at Europol and the nine European Union Member State LEAs within the consortium. The goal for GRACE is to attempt to provide results early, frequently and flexibly, prioritising easy wins in the research plan (e.g. deduplication).
Unique to GRACE is the development and application of a Federated Learning approach to the challenge of optimising analysis and information flow in a privacy-aware and security-sensitive manner. GRACE will enable cooperation between LEAs in improving their capabilities while harnessing their experiential knowledge.
The results of GRACE will be available to Europol and the Member State LEAs for unrestricted use in their operations, helping to ensure their future technological autonomy.
In the initial phase of the project, reported in this Periodic Report Nº 1, the consortium focused on:
• Organisation of co-creation and cross-collaboration activities to advance on technological understanding and to bring the technology vision to the practitioners and to align the development activities with their needs, expectations and practice;
• Collect end user requirements and draft the specific use cases to drive the project development;
• Development of a unified categorisation and classification of the investigative information, i.e. a common ontology, transversal to all technical WPs and potentially transferable beyond the project;
• Ingestion of referrals from relevant NGOs and OSP/s through NCMEC reports, being the principal source of CSEAM reports;
• Development of a variety of audio, video and text analytics modules to extract investigative relevant leads from multimedia sources;
• Developing higher knowledge analysis tools to infer investigative value from the available report data, such as relevance classification and prioritisation;
• Setting up the essential prerequisites for the development of a Federated Learning platform, i.e. the supporting infrastructure as well as the indispensable data annotation tools and strategies;
• Drafting the collaboration platform front-ends and functionalities;
• Organising the initial “First Look” pilot to evaluate the early developments of the GRACE platform;
• Extended analysis of the available legislation and national frameworks to drive the GRACE developments and draft ways for cross-border collaboration;
• Visibility of the project through web and social media means and collaboration with sister projects, networks and initiatives;
• Initial exploitation strategies and policy relevant considerations have been elaborated;
• Extensive recommendations addressed to the policy makers in order to be effective in defining the legislation and the policies to fight CSE crimes;
• Practical guidelines for the first responders with the aim to translate them in dedicated trainings.
The objectives of the first period have been attained, despite minor delays noticed immediately after the project start and which have been caused by COVID-19 restrictions impacting mobility and face to face meetings and communication.
• Organisation of co-creation and cross-collaboration activities to advance on technological understanding and to bring the technology vision to the practitioners and to align the development activities with their needs, expectations and practice;
• Collect end user requirements and draft the specific use cases to drive the project development;
• Development of a unified categorisation and classification of the investigative information, i.e. a common ontology, transversal to all technical WPs and potentially transferable beyond the project;
• Ingestion of referrals from relevant NGOs and OSP/s through NCMEC reports, being the principal source of CSEAM reports;
• Development of a variety of audio, video and text analytics modules to extract investigative relevant leads from multimedia sources;
• Developing higher knowledge analysis tools to infer investigative value from the available report data, such as relevance classification and prioritisation;
• Setting up the essential prerequisites for the development of a Federated Learning platform, i.e. the supporting infrastructure as well as the indispensable data annotation tools and strategies;
• Drafting the collaboration platform front-ends and functionalities;
• Organising the initial “First Look” pilot to evaluate the early developments of the GRACE platform;
• Extended analysis of the available legislation and national frameworks to drive the GRACE developments and draft ways for cross-border collaboration;
• Visibility of the project through web and social media means and collaboration with sister projects, networks and initiatives;
• Initial exploitation strategies and policy relevant considerations have been elaborated;
• Extensive recommendations addressed to the policy makers in order to be effective in defining the legislation and the policies to fight CSE crimes;
• Practical guidelines for the first responders with the aim to translate them in dedicated trainings.
The objectives of the first period have been attained, despite minor delays noticed immediately after the project start and which have been caused by COVID-19 restrictions impacting mobility and face to face meetings and communication.
GRACE is developing an innovative platform that paves the road to the novel interaction between EUROPOL and MS LEAs, that is aligned with the new Europol's mandate on fighting cross-border crime and strengthening the cooperation between EU MS. On a long term, the GRACE project will provide a reference framework for the future policies and the mandate of the new establishing EU Centre.
GRACE will drive the adoption of cutting edge technologies to the peculiarities of the CSEM fight domain. It is developing a wide register of novel forensic analysis tools based ML technologies for rapid inspection of audio-visual and textual material, and contributing to the research on CSEAM-specific content analysis, classification, geo-localisation, evidence-graph creation and knowledge mining, case prioritisation and predictive trend analysis.
Central to the GRACE project is the adoption of a Federated Learning (FL) platform that is being designed and tested to train or tune the corresponding ML techniques on real data dispersed across MS LEAs. This novel approach will increase the capability of adapting the analytics to CSEM domain, while inherently implementing high standard principles of data privacy and security.
The work performed so far in the various WPs is addressing the LEAs’ operational needs by continuously collecting the feedbacks in order to tailor the GRACE platform, tools and data model on their operational needs. To this end, GRACE counts with an initial, automatised data ingestion pipeline and more than 30 standalone analysis tools that have been prepared under tight supervision by the LEA partners, who provided insights on their usability and further improvements.
Along with the technical work, GRACE also investigates on the necessary legal framework for the use of the AI tools and prevention of risks, as well as the related CSEA legislation in place, to help identify any harmonisation needs for establishing an effective MS collaboration framework at the EU level.
To this end, work has been released that provides an overview of best practices and policy adopted by the LEAs, recommendations on a standard approach towards the victims, as well as effective actions to arrest offenders. While the documents are specific to the GRACE project and the tools and frameworks implemented therein, they shall provide insights for possible debate at the policy level related to the EU strategy for an effective fight against CSA.
GRACE will drive the adoption of cutting edge technologies to the peculiarities of the CSEM fight domain. It is developing a wide register of novel forensic analysis tools based ML technologies for rapid inspection of audio-visual and textual material, and contributing to the research on CSEAM-specific content analysis, classification, geo-localisation, evidence-graph creation and knowledge mining, case prioritisation and predictive trend analysis.
Central to the GRACE project is the adoption of a Federated Learning (FL) platform that is being designed and tested to train or tune the corresponding ML techniques on real data dispersed across MS LEAs. This novel approach will increase the capability of adapting the analytics to CSEM domain, while inherently implementing high standard principles of data privacy and security.
The work performed so far in the various WPs is addressing the LEAs’ operational needs by continuously collecting the feedbacks in order to tailor the GRACE platform, tools and data model on their operational needs. To this end, GRACE counts with an initial, automatised data ingestion pipeline and more than 30 standalone analysis tools that have been prepared under tight supervision by the LEA partners, who provided insights on their usability and further improvements.
Along with the technical work, GRACE also investigates on the necessary legal framework for the use of the AI tools and prevention of risks, as well as the related CSEA legislation in place, to help identify any harmonisation needs for establishing an effective MS collaboration framework at the EU level.
To this end, work has been released that provides an overview of best practices and policy adopted by the LEAs, recommendations on a standard approach towards the victims, as well as effective actions to arrest offenders. While the documents are specific to the GRACE project and the tools and frameworks implemented therein, they shall provide insights for possible debate at the policy level related to the EU strategy for an effective fight against CSA.