You are here
Google engineer developing tool to make and spot fake videos
IN AN era replete with fake news stories, you might expect video evidence to provide a clearer picture of the truth.
You would be wrong, says Google engineer Supasorn Suwajanakorn.
He has developed a tool which, fed with the right input, can create a realistic fake video that mimics the way a person talks by closely observing existing footage of their mouth and teeth to create the perfect lip-sync.
Like any technology, it has great potential for both good and mischief.
Mr Suwajanakorn is also working with the AI Foundation on a "Reality Defender" app that would run automatically in web browsers to spot and flag fake pictures or videos.
"I let a computer watch 14 hours of pure Obama video, and synthesized him talking," he said, as he sharing his shockingly convincing work at the TED Conference in Vancouver on Wednesday.
Such technology could be used to create virtual versions of those who have died: grandparents who can "return" and be asked for advice; actors who can make comebacks to the screen; great teachers could deliver lessons again, or authors read their works aloud, he said.
He noted that a "New Dimensions in Testimony" project is giving people opportunities to have conversations with holograms of Holocaust survivors.
"These results seemed intriguing, but at the same time, troubling; it concerns me, the potential for misuse.
"So, I am also working on counter-measure technology to detect fake images and video."
He is concerned, for example, that war could be triggered by bogus video of a world leader announcing a nuclear strike.
The "Reality Defender will automatically scan content for manipulated pictures or video, and will also have a facility for users to report apparent fakes, thus using the power of the crowd to bolster the defence.
"Video manipulation will be used in malicious ways unless counter-measures are in place," he told AFP.
"We have to make it very risky and cost-ineffective." While writing fake news may be cheap and easy, it is tough to manipulate video without any traces, he noted. Videos, by design, are streams of thousands of images, each of which would have to be perfected in a fake.
"There is a long way to go before we can effectively model people," said the engineer, whose work in the field stems from his time as a student at the University of Washington.
"We have to be very careful; we don't want it to be in the wrong hands." AFP