Ruslan Grumble - Fotolia
Home Office has joined forces with London-based ASI Data Science to launch a tool to detect terrorist content in videos uploaded on the web.
The tool uses advanced machine learning to analyse audio and visual content for terrorism propaganda, and the Home office and ASI will be sharing the methodology behind the technology with smaller companies, which may not be able to develop their own.
The tool is platform agnostic and can be used to find terrorist content across almost any video-streaming or download sites in real-time, according to the Home Office.
Home secretary Amber Rudd said the department has been engaging with internet companies “to make sure their platforms are not being abused by terrorists and their supporters”.
“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,” she said.
“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.”
Rudd added that she hopes the “new technology the Home Office has helped develop can support others to go further and faster. This government has been taking the lead worldwide in making sure that vile terrorist content is stamped out.”
Testing of the tool has shown that it can automatically detect 95% of Daesh propaganda with nearly 100% accuracy (99.995%), according to the Home office. It can also be integrated into the video upload process to stop the video from ever being published online.
Read more about terrorism and technology
- The UK is calling on social media campaigns to do more to detect and remove “militant messaging” automatically.
- Prime minister Theresa May presses internet companies to develop technical solutions that will allow terrorist material to be taken down from the internet in under two hours.
The home secretary is currently in the US, planning to attend several meetings on tackling terrorist content online.
During another trip to the US last year, Rudd said although social media companies were working to tackle terrorist content and improvements are being made, there was “much more” companies could do to improve their response times even further, such as by harnessing artificial intelligence (AI) and other emerging technologies.
Read more on Security policy and user awareness
Government puts Facebook under pressure to stop end-to-end encryption over child abuse risks
Tech companies should not be under legal duty to remove terrorist material, says watchdog
UK and allies call for backdoors in encryption products
EC calls on online platforms to develop common code of practice to tackle ‘disinformation’