New Software Predicts Who’s A Terrorist

New Software Predicts Who’s A Terrorist

This post is also available in: heעברית (Hebrew)

A good poker face used to mean that no one could tell what you’re thinking. An Israeli startup is shattering this reality with a new face-profiling technology that can (almost) read your mind.

Faception recently demonstrated its technology by predicting which four players in an amateur poker tournament were most likely to beat 46 other players. Two of the four were among the three finalists in the competition.

Faception isn’t limiting itself to poker, however, and claims to be able to identify terrorists with the aid of the technology, which analyses facial features in images and video according to 15 parameters predictive of personality types and traits. The company says it can determine with high accuracy whether you’re an extrovert, genius, or criminal.

“We understand the human much better than other humans understand each other,” Faception CEO Shai Gilboa told the Washington Post. “Our personality is determined by our DNA and reflected in our face. It’s a kind of signal.”

Certain traits can be analysed with accuracy of up to 80 percent, Gilboa said.

“Utilizing advanced machine-learning techniques, we developed and continue to evolve an array of classifiers. These classifiers represent a certain persona, with a unique personality type, a collection of personality traits or behaviors. Our algorithms can score an individual according to their fit to these classifiers.

“Ultimately, we can score facial images on a set of classifiers and provide our clients with a better understanding of their customers, the people in front of them or in front of their cameras.”

And apparently it works. Despite the fact that only three of the eleven terrorists involved in the November 2015 Paris attacks had criminal records, and thus only these three would have been identified by other face recognition software, Faception’s algorithms “classified nine of them as potential terrorists with no prior knowledge,” said Gilboa.