$7 million raised, including Google, to authenticate people based on a specific typing style
TypingDNA, a four-year-old company with a 18-person startup that was founded in Bucharest, Romania and more recently moved its headquarters to Brooklyn in New York; has closed on $7 million funding for AI-driven technology apparently capable of recognising people based on the way they type, both on their laptops and mobile devices.
In 2018 and early last year they closed on €1.3 million in seed funding and had so far raised $5.25 million toward that goal. I’ve since connected with the company’s co-founder and reached out to their CEO, Raul Popa, who confirms the entire amount has been raised for the project.
Gradient Ventures, which is Google’s nearly three-year-old, AI-focused venture group, led the round; as it too was joined by the company’s previous backers, including Techstars Ventures and GapMinder Venture Partners, a venture outfit based in Amsterdam.
The typing biometrics hold the detailed timing information that describes exactly when each key is pressed and released as a way to identify the unique person at the keyboard based on their key strokes. The idea and concept is apparently not brand new either.
According to a new source I’ve recently read that an article says research in this field for typing biometrics dates back 20 years. It also says that inaccuracies have kept the technology from being used as a widespread way to authenticate individuals. TypingDNA meanwhile asserts that the typing pattern recognition technology has developed with progress and has an accuracy rate of between 99% and upwards of 99.9%.
According to Popa, TypingDNA is currently working with banks, financial and payment apps, online education platforms, enterprise apps, consumer apps, and government apps that are concerned with identity and fraud prevention.
On the education front, for example, it helps organisations to ensure they’re giving the right students credit for the work they receive.
Worth noting: its API is open to anyone, especially developers which means its likely opensource or under similar licensing and looking into integrate the technology with their products and apps. I asked how the company will use its new round, Popa says
the plan involves “focusing on developers more, and coming up with typing biometrics based products that can easily be integrated to solve various use cases, and helping banks and tech companies where regulation asks for biometrics as a second factor.”
As for what TypingDNA is doing that wasn’t previously possible, Popa then says
his team doesn’t need a huge body of work to draw conclusions, that they’re “able to look at very short and few samples of text in order to authenticate people with great accuracy.” The mobile tech, he says, “needs even less data than on desktop, because we also look at other sensors in the device.”
From an AI point of view, TypingDNA is apparently combining pattern recognition, anomaly detection, and what Popa calls one-shot learning techniques. Some of which are “completely novel,” he says. Indeed, if all goes as planned, it might eventually be applied to other technologies, as well as to improve binary classification quality when few training samples are used.
Conclusion
While it might be a while before this type of technology is solely trusted as an alternative algorithm to determine which individual is sitting at the PC or the device being used. It may so happen that this new software may also be used in conjunction with already existing functionality to add clarity to which user is currently logging into a PC, Mobile or any other computer device. And since it is already working with Banks, and other companies I believe we will be seen a lot more of TypingDNA and its algorithm.