An app designed to detect “deepfakes” took home the grand prize at PennApps XX, beating nearly 250 tech projects developed over the course of a weekend, the University of Pennsylvania School of Engineering and Applied Science announced in a Sept. 10 news release.
The team, DeFake, was led by Indian Americans Aarati Srikumar and George Diwan, and included teammates Daniel Li and Sofiya Lysenko.
The top three team members took home a bevy of tech items, software subscriptions and gift cards; nearly $100,000 worth of prizes were awarded across a variety of technical categories, the news release said.
PennApps, the nation’s first student-run college hackathon, was founded in 2009 and has been running biannual invitational events since.
Contestants from around the world form teams and come up with ideas for digital apps or hardware projects, which they must complete before a demo session.
There, the projects are evaluated by a panel of tech industry judges, who rate them on originality, technical difficulty, polish, and usefulness, the release noted.
DeFake’s winning project was a browser extension that uses machine learning to assess the likelihood that a given video has been subtly manipulated.
Deepfakes are a new method of using artificial intelligence to impersonate famous figures, using pre-existing video and audio clips to generate photo-realistic fabrications, the university said.
Worried about deepfakes being “particularly influential in the outcome of this and future elections,” the team “wanted to develop a level of protection and reality for users,” it said.
In second place was Jaught, a virtual whiteboard system that allows users to share notes and teach lessons using a web-camera. ImpromPPTX took third place. The app automatically generates a slideshow presentation in real time, based on what the speaker is saying.