University of Amsterdam launches research in using AI to fight crime
Research by UvA and Netherlands Forensic Institute will focus on developing computer models that can detect deepfakes and hidden messages used by criminals.
UvA and NFI join forces to fight crime with AI
A joint research initiative by the University of Amsterdam (UvA) and Netherlands Forensic Institute (NFI) will look into developing AI that can help police and prosecutors collect forensic evidence.
The research at the Innovation Center for Artificial Intelligence will focus on the development of AI-powered computer models that have been taught to detect deepfake videos and hidden messages (steganography).
Criminals are increasingly making use of deep fakes, said Professor Zeno Geradts, one of the driving forces behind the lab and a researcher at the NFI and special chair of Forensic Data Science at the UvA’s Faculty of Science: “It’s used to make adults in child porn films unrecognisable, for example. Or to influence opinions using computer-generated people. It’s almost impossible to distinguish between real and deepfake videos with the naked eye.”
“Existing computer models can detect deepfake in about eight out of ten videos. In other words, it’s still not being detected in two out of ten videos. What we really want, however, is for at least 99.5% of deepfakes to be removed.”
The research will also include how AI can be used to read data from mobile phones and car sensors, which could be used to bolster evidence in criminal cases.
Knowledge-sharing
The studies are a good example of the knowledge-sharing initiatives between academia, public bodies and businesses in the Amsterdam Area. UvA’s researchers can develop the most cutting-edge methods in criminal investigations with the help of knowledge from the forensics experts. This will prepare the NFI to respond to forensic demands of the future.
Professor Peter van Tienderen, dean of the Science Faculty, added: “The lab collaboration with the NFI fits perfectly Amsterdam’s vision for AI: together with our partners we develop digital technologies that prevent abuse and contribute to society.”
Considered one of the most AI-ready cities in the world, Amsterdam is committed to developing AI that improves healthcare, business and citizen support. The AI Technology for People programme is helping the city design and deploy responsible AI in these areas . The Dutch capital is also proving to be an effective ‘living lab’ for forward-thinking startups testing AI solutions. Amsterdam-founded Sensity has gained international recognition for its work in using AI to detect deepfake material and disinformation.