Developed by the UK Home Office and London-based company ASI Data Science, the technology uses advanced machine learning to analyse the audio and visuals of a video to determine whether it could be ISIS propaganda.
The Home Office said in a statement yesterday that its new tool can automatically detect 94 per cent of ISIS propaganda with 99.995 per cent accuracy.
The purpose of these videos is to incite violence in our communities, recruit people to their cause, and attempt to spread fear in our society. We know that automatic technology like this can heavily disrupt the terrorists actions, as well as prevent people from ever being exposed to these horrific images, UK home secretary Amber Rudd said in reference to the new tool.
The announcement came as she addressed a Digital Forum in Silicon Valley during a US visit this week.
More From This Section
She discussed the new anti-terror tool on her visit during talks with internet service providers in the country as part of the Global Internet Forum to Counter Terrorism, which was launched last year in the aftermath of the UK Parliament attack in March 2017.
The Home Office and ASI said they will be sharing the methodology behind the new model with smaller companies, in order to help combat the abuse of their platforms by terrorists and their supporters.
But smaller platforms are increasingly targeted by ISIS and its supporters and they often do not have the same level of resources to develop technology.
The model, which has been trained using over 1,000 ISIS videos, is not specific to one platform so can be used to support the detection of terrorist propaganda across a range of video-streaming and download sites in real-time, the Home Office said.
Previous research has found the majority of links to ISIS propaganda are disseminated within two hours of release, while a third of all links are disseminated within the first hour. The new research also shows 145 new platforms from July 2017 until the end of the year had not been used before.