Social app Gen Z Yubo deploys age estimation technology to better identify minors using its service – TechCrunch
Yubo, a social live-streaming app popular with a Gen Z audience, today announced that it is becoming one of the first major social platforms to adopt a new age verification technique that uses live image capture technology to identify minors using its app, to keep them separated from adult users. While other companies serving a younger customer base typically rely on traditional age verification techniques, these are easily circumvented as all that is usually required is for a user to enter a date of birth into an online form.
Many children know that they can lie about their age to gain access to platforms designed for older users, which is how they end up in online spaces that are not child-friendly or have more great risks associated with their use.
Yubo, on the other hand, thought about what the future of social media should look like for the next generation of users – and not just from a product perspective, but also from a product security perspective. .
Founded in 2015, Yubo users hang out in live streaming rooms where they can socialize, play games, and make new friends. There are no creators on the platform streaming to fans, and Yubo has no plans to go in that direction – like almost every other major social platform has today. . Instead, the goal of his app is to help users socialize naturally, as they are already comfortable with, having grown up using FaceTime services and hanging out with friends in other video apps. live.
According to Yubo co-founder and CEO Sacha Lazimi, Gen Z sees “no difference between online and offline life,” he says.
“They have exactly the same socialization needs offline as online, but there were no solutions [for this]“says Lazimi. This led to Yubo launching a live video feature which was launched to the app’s user base in February 2018.
“We take the best of offline interaction and add the power of technology to make sure you’ll connect with the right group of people anywhere in the world, anytime, in a safe environment.” he.
The company had 60 million sign-ups today, up from the 40 million it reported in 2020 when it closed its $47.5 million Series C funding round. 99% of them are Gen Z users, aged 13-25.
While Yubo doesn’t share its monthly active users, it does note that it’s seeing an increase in revenue through its premium pay-per-view features and subscriptions, which have grown from €7 million in 2019 to €25 million this year. last year. The application does not serve advertisements.
But with this younger audience and growth, comes the need for increased security. Previously, Yubo partnered with digital identity provider Yoti to help vet potentially suspicious users. If people were using different phone numbers or devices, for example, or were reported by others, Yubo would ask them to verify themselves by submitting their credentials. The identity verification management process was handled by Yoti.
On average, Yubo processed 6,500 verifications per day in 2021. As a result of this verification, 67,000 accounts per month were suspended due to age differences, the company says.
But there was a challenge with this system – minors often don’t have ID.
“A lot of teenagers – especially those under 18 – don’t have identity papers,” notes Lazimi. “So we couldn’t ask everyone to verify their identity.”
This led the company to adopt another Yoti product for age estimates. This system will direct new and existing users to an age verification and consent screen either during registration or as a pop-up window for existing users when launching the app. When they accept, their camera activates and they are prompted to place their face in an oval that appears on the screen. The “vividness algorithm” also takes a short video that analyzes motion to confirm that the image used is not fake or pulled from a search engine.
When the face has been detected, the user will receive a confirmation that they have been verified or they will be told if their age does not match the age they entered during registration or if they are not using not a legit photo.
If the age of the user is confirmed, he will be directed to the home page and can use Yubo as before. If the verification fails, they will have to go through a full identity verification instead.
The new technology, as you can imagine, is not perfect.
Lazimi admits it works better with young faces than adults. Currently, the Yoti age estimation system can efficiently identify user ages from 6 to 12 in 1.3 years, and those between 13 and 19 in 1.5 years, Yoti claims. After that, the accuracy decreases. For 20 to 25 year olds, it is accurate within a 2.5 year range. For 26-30 year olds, it’s an average of 3 years. But this accuracy may improve over time as more analyzes are performed.
“It’s actually very accurate for younger users, and especially users under 15…I think for 13-14 year old users, it’s about 99%,” he says. (It’s 98.9 percent accurate for all ages, genders, and skin tones, Yoti says.) To date, Yoti has used the technology on some 500 million faces and is certified by software testing service iBeta.
“It’s less accurate for older users – that’s why we launched with younger users, because those are the ones we want to protect more and also because it’s more accurate and precise,” explains Lazimi.
The company will initially roll out the technology to users aged 13 and 14 with the aim of verifying the age of 100% of users by the end of 2022.
Age estimation technology isn’t the first tool Yubo has adopted to keep young users safe on live streams, the company points out.
It also uses AI technology and human moderation to monitor live streams by taking second-by-second screenshots and then reporting inappropriate content to human moderators in real time, including nudity, nudity partial (including underwear), suggestive content, drug use, weapons, blood and violence. (You can see some complaints about this in Yubo’s App Store reviews, where teens complain that it flagged boys that they were streaming shirtless.)
Yubo also includes educational safety features. For example, the app displays pop-up reminders about custom editing options (like mute words) and sends alerts to users if they engage in harmful and inappropriate behavior or share sensitive personal information. The company also has a Security Advisory Board made up of international online security experts.
“We also work closely with government and NGOs as we believe social media needs to be regulated more from the top,” says Lazimi. But, he adds, “we don’t wait for regulations to make safety devices. We do this proactively,” he says.