Software developed with ASI Data Science will be made available for smaller platforms lacking resources for their own
The Home Office has announced the development of a software tool to automatically detect content from the Daesh terrorist group on any online platforms.
It has been working with London based ASI Data Science on the technology, which uses advanced machine learning to analyse the audio and visuals of a video to determine whether it could be terrorist propaganda.
The two are planning to share the methodology behind the new model with smaller companies, in order to help combat the abuse of their platforms by Daesh and their supporters.
The Home Office said tests have shown the tool, which has been trained using over 1,000 Daesh videos, can automatically detect 94% of propaganda from the group with 99.995% accuracy.
It can be used by any platform, and integrated into the upload process, so that the majority of video propaganda is stopped before it reaches the internet.
Some major tech companies have developed technology specific to their own platforms and have publicly reported on the difference this is making in their fight against terrorist content. Smaller platforms, however, are increasingly targeted by Daesh and its supporters and they often do not have the same level of resources to develop technology.
While the software is initially directed at Daesh, there is a potential for the methodology behind it to be applied to content from other terrorist sources.
More to do
Home Secretary Amber Rudd said: “Over the last year we have been engaging with internet companies to make sure that their platforms are not being abused by terrorists and their supporters. I have been impressed with their work so far following the launch of the Global Internet Forum to Counter-Terrorism, although there is still more to do, and I hope this new technology the Home Office has helped develop can support others to go further and faster.
“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.”
The Home Office also runs an online channel, currently in public beta, for reporting any material that promotes terrorism or extremism. It asks users to identify the web addresses of sites where they have found the content.
Recent analysis by the department has demonstrated that Daesh supporters used more than 400 unique online platforms to push out their material in 2017, highlighting the importance of technology that can be applied across different platforms. Previous research has found the majority of links to Daesh propaganda are disseminated within two hours of release, while a third of all links are disseminated within the first hour.
The new research also showed that 145 platforms, not used before by the group, had been exploited from last July until the end of the year.
The announcement has come as Rudd travels to Silicon Valley for a series of meetings with the main communication service providers to discuss tackling terrorist content online. She is expected to discuss the new model on her visit to find out what companies are doing to develop innovative methods that identify Daesh propaganda, and support smaller companies, such as Vimeo, Telegra.ph and pCloud to remove terrorist content from their platforms.
She will also meet US Secretary of Homeland Security Kirstjen Nielsen to discuss how the UK and US can work together to tackle terrorist content online, and with the Global Internet Forum to Counter Terrorism, which was launched last year following a roundtable convened at the Home Office in the aftermath of the Westminster Bridge attack.
Images from GOV.UK, Open Government Licence v3.0