Articles

Woman surrounded by green plants using her smartphone

Age Check Certification Scheme evaluation for Yoti Facial Age Estimation

We are pleased to announce Yoti has been re-evaluated by the Age Check Certification Scheme (ACCS) for our facial age estimation (FAE) on our latest September 2024 model. ACCS now report our Mean Absolute Error (MAE) for 18 year olds is just 1.05 years, with a Standard Deviation (SD) of just 1.01 years. ACCS first tested Yoti’s September  2020 model in November 2020, reporting the MAE for 18 year olds to be 1.79, demonstrating our continued effort to improve the performance of our model.   Yoti has been training its FAE model since early 2018 by using data captured mainly

3 min read
An image of Robin with accompanying text that reads "Thoughts from our CEO, Robin Tombs, October 2024".

Thoughts from our CEO

In this blog series, our CEO Robin Tombs will be sharing his experience, whilst focusing on major themes, news and issues in the world of identity verification and age assurance. This month, Robin gives a summary of the upcoming legislation for online porn in France, responds to Ofcom’s claims that facial age estimation is not effective for under 13s, and looks at the upcoming Digital Information and Smart Data Bill.   French regulator introduces age checks for online adult content Big news this month that Arcom, the French regulator responsible for online porn, has announced the date that platforms

8 min read
An image of a young boy who is wearing a red hoodie and looking down at his mobile phone. The accompanying text next to the image reads “Minors’ access to pornographic content: France”.

French regulator Arcom introduces age checks for online adult content

In October 2024, Arcom, the French regulator responsible for online porn, announced that adult operators and platforms with pornographic content need to introduce age checks, ensuring only adults can access the content. These rules are effective from 11th January 2025. There will be a three month transitional period, where temporary methods like bank card verification can be used as a preliminary age filter, but they must include strong authentication to ensure that the user is the cardholder. After the transitional period ends on 11 April 2025, adult site operators will need to have taken the following steps: Age checks

5 min read
Image of a hand holding a mobile phone which says "sensitive content" on the screen. The accompanying text reads "Online Safety Act - United Kingdom".

Understanding age assurance in the Online Safety Act

The Online Safety Act 2023 is a piece of UK legislation that aims to protect children and adults online. It covers a wide range of issues including minimising the risk of children seeing harmful and age-inappropriate content, removing illegal content like child sexual abuse material (CSAM), criminalising fraudulent and scam ads, and introducing age verification for certain online services. This blog looks at some of the age requirements in the Online Safety Act and what this means for tech companies, adult sites, gaming companies, social media platforms and dating sites.   What is the purpose of the Online Safety

11 min read
Decorative image of the outside of the Houses of Parliament.

Welcoming the new Regulatory Innovation Office

This week, the UK Government announced the creation of the new Regulatory Innovation Office – a move we welcome here at Yoti.  Bringing new tech to market is often slowed down, or even blocked, due to outdated regulations or a lack of existing bodies to help support and facilitate the introduction of the new technology or co-ordinate its joint recognition. Recognising that this is a barrier to innovation, the Government will introduce the Regulatory Innovation Office (RIO).  The Regulatory Innovation Office will sit under the Department for Science, Innovation and Technology (DSIT). It aims to help regulators facilitate economic

4 min read
A man placing his face in the frame to perform a facial age estimation with Yoti

How accurate is facial age estimation?

“How accurate is it?” is the first question regulators, businesses and users tend to ask about facial age estimation. To date, we have mainly presented the technology’s Mean Absolute Error (MAE) as a proxy for accuracy. It’s an intuitive way to understand how accurate a model is. We can say it’s accurate to 1.3 MAE for those aged between 13 and 17 years or 2.5 MAE for those aged between 6 and 70 years. However, the answer is slightly more complicated. Following the COVID-19 pandemic, many people will be more aware of the terms ‘true positive’ and ‘false negative’

5 min read