Save time, save lives

Reports of Child Sexual Abuse Material (CSAM) are labour-intensive to process. AviaTor, which stands for Augmented Visual Intelligence and Targeted Online Research, is an efficient tool that helps prioritise all aspects of NCMEC reports so law enforcement can focus on identifying perpetrators and saving victims.

Law Enforcement Agencies (LEAs) across the globe receive reports of potential Child Sexual Abuse Material (CSAM) from the National Center for Missing and Exploited Children (NCMEC). Companies in the United States like Facebook and Google are required by law to proactively scan their systems for potential CSAM. This results in a huge quantity of NCMEC reports. In 2018, NCMEC’s CyberTipline, INHOPE's U.S. hotline, received more than 18 million reports of potential CSAM from US based companies. In 2020, this number rose to 21.7 million.

The large increase of material every year puts an unsustainable workload on law enforcement agencies so requires the use of prioritisation tools to swiftly identify children in real danger. The AviaTor project was conceptualised with this purpose in mind.

The objective

Reduce the time spent on NCMEC reports by law enforcement agencies.

AviaTor was developed for law enforcement with the support from 16 law enforcement agencies across Europe. There are Law Enforcement Agencies (LEAs) that are currently having to use temporary solutions to classify and prioritise cases of Child Sexual Abuse Material, which is a short term-fix. AviaTor is the long-term solution that can automatically crawl online sources for additional information for investigations in accordance with the national legal requirements. The National Police of the Netherlands have been using the first version of the AviaTor tool since December 2019.

How does AviaTor work?

There are three key elements of AviaTor.

Database

Basic database functions save time on triage, searching, clustering, and tracking distribution of the workload. AviaTor has a plug-in system which includes a number of visual and text analysis steps.

Prioritisation

Reports are prioritised using different rules, like the number of files uploaded by a user, and whether a user has been previously reported. These rules can be customised to specific needs.

Targeted crawling

Predefined checks to automatically enrich the NCMEC report, with for example the status of a social media profile or the user’s occupation such as those working with children.

What can AviaTor do for you?

Improving LE wellness

The stress and psychological impact on Law Enforcement of the impossible workload of manually performing all of the search activity to identify offenders is huge. By reducing the amount of labour required, AviaTor plays a crucial role in improving their wellness.

Preventing bias

A lot of research is performed by the tool before LEAs identify new indicators or make judgements about the dangerousness of a person. This can help avoid crucial errors.

Avoiding lost data

LEAs must work against the clock to get data which helps identify the perpetrator before the data retention time lapses and it is no longer accessible. AviaTor indicates this information with the report, meaning LEAs are able to prioritise cases before it’s too late.

Making the impossible possible

AviaTor can help countries without the infrastructure to handle large volumes of reports, putting LEA back in control of overwhelming numbers of reports.

More information

If you are a law enforcement agency representative and are interested in this project, please sign-up for a demo via our partner INHOPE or contact us for information.

EU Project
This project was funded by the European Union’s Internal Security Fund – Police under Grant Agreement No. 101038713