AI on the front line to block online child grooming
A new technique that uses artificial intelligence to identify and block child grooming conversations online has been launched by the Home Office and Microsoft.
Code-named Project Artemis, it began development at a hackathon co-hosted by Microsoft and the Home Office in November 2018. It will automatically flag conversations that could be taking place between groomers and children, and pass on details of the flagged conversation to the relevant law enforcement agency.
It is being licensed free of charge to small and medium-sized technology companies to help them stamp out child grooming on their platforms.
The prototype was developed in Seattle in 2018. Engineers from Microsoft, Facebook, Google, Snap and Twitter worked for two days analysing thousands of conversations to understand patterns used by predators.
Since then, engineers have worked through technical, legal and policy aspects, analysing thousands more instances of grooming conversations to develop the technique. The work was led by a cross-industry group spearheaded by leading academic Dr Hany Farid, who had previously worked to develop a tool that assisted in the detection, disruption and reporting of child exploitation images.
Minister for Safeguarding and Vulnerability Victoria Atkins said: “Online grooming of children is utterly sickening, which is why it’s vital to drive innovation to tackle this appalling crime. The launch of this technology represents the culmination of months of hard work by those committed to keeping our children safe online.”