Learning more about our facial age estimation
Facial age estimation is a valuable age assurance tool helping industries to provide age appropriate products and services worldwide. Using a combination of AI technology and liveness anti-spoofing, our tools are helping businesses know their customers are the right age to access their product or services without knowing anything more about them. We want to make sure you have all the information you need to navigate facial age estimation. We’ve compiled some excellent resources that help to explain the core technology and why we’ve developed our solution the way we have. How facial age estimation is built How AI really works Try Yoti’s facial age estimation demo Putting our anti-spoofing technology to the test Facial age estimation in use Peer-to-peer checks: know who you’re dealing with Further reading How age estimation is built We partnered with family digital wellness experts Be inTouch to explain how we built our facial age estimation technology. Watch his three minute video below. How AI really works You can also check out the below two-part series where Be inTouch explains how AI really works. In the eight minute and twelve minute explainer videos, you can learn more about AI, deep learning, and how it’s used to estimate age and create safe spaces online. Try it out with our demo (for users aged 13 and above) Using our facial age estimation is simple. Check it out for yourself in our interactive demo. Putting our anti-spoofing technology to the test We’ve implemented anti-spoofing to make sure that people can’t imitate someone older or younger than their actual age and trick our age estimation tech. It works by using deep machine learning, preventing presentation attacks. We put our anti-spoofing technology to the test to see if our facial age estimation can outsmart a disguise. Watch the thirty-second video below to see what happened. Facial age estimation in use Our tech provides many real life benefits to people of all demographics. See what these students at Queen Mary University had to say about Yoti facial age estimation and the future of ID checks in our one-minute video. For these shoppers in Estonia, the checkout process just got a whole lot faster. We visited the first supermarket in the world using age estimation in their self checkout terminals. Watch the thirty-second video to see what they thought. Peer-to-peer checks: know who you’re dealing with When you’re talking to people online, it’s almost impossible to know who you’re dealing with from just a profile picture. Whether you’re online dating, buying a bike from a shared marketplace, or organising a holiday let, make sure you know exactly who you’re talking to. Our Little Casanova shows us just how easy it is to misjudge how old someone might be before you meet them in person in this two-minute video. Further reading For even more information on our age estimation technology, or our other age assurance tools, check out our blogs. Tackling child sexual abuse online with the Safety Tech Challenge Fund Online age verification: a new era Age verification: the solution to buying age-restricted products in supermarkets Developing age estimation technology to tackle grooming online To read more about facial age estimation and the steps we’ve taken to get to where we are today, you can read our full briefing materials here.
How the Yoti app is complying with the ICO’s Age Appropriate Design Code
Following the end of its 12-month transitional period, it is now a legal requirement for businesses to comply with the ICO’s Age Appropriate Design Code (the Code). It will affect any business operating online whose services are likely to be used by children in the UK, specifically in industries such as social media, video or music streaming, gaming or education. Providing safer environments for children in the digital economy The Code sets out 15 standards that aim to create a safe space for children to learn, explore and play online. It aims to empower children to be safe online by increasing their data privacy awareness, making language simpler and treating them fairly, whilst minimising data collection. By conforming to the Code, businesses are deemed to be acting in the best interest of the children using their online services. Encouraging this default safety setting, children can safely access digital services whilst minimising the collection and use of their data. How we’re taking action As a company, our work is guided by an ethical framework, developed in line with the GDPR and key principles such as Privacy by Design. As such, we found a strong alignment with the Code but we wanted to focus on two of the fifteen standards: “Best interests of the child: When you design and develop online services a child is likely to access, the best interests of the child should be a primary consideration.” “Transparency: The privacy information you provide to users, and other published terms, policies and community standards, must be concise, prominent and in clear language suited to the age of the child. Provide additional specific ‘bite-sized’ explanations about how you use personal data at the point that use is activated.” So we started off with user research. We specifically wanted to see how well a group of teenagers understood our app, age estimation process, services, terms and privacy policy. This helped us pinpoint concepts that were difficult to understand, as well as how easy it was for our users to find information about how their data is used. Our findings encouraged us to change aspects of our app content, our communications and our privacy information. Changing the content in our app We are committed to making our app as easy to use as possible for people of all ages. We used the results from our user research to optimise important content to be certain that it would be widely understood. We made sure our titles provided greater context and included subtitles to make screens scannable. We explained in greater detail any words that might not be easily understood by younger people, like ‘encrypted’. In other cases, we avoided using words that could be considered too broad in a given context. For example, we no longer use the word ‘biometrics’ on our age-gating primer screen and instead swapped it out for the phrase ‘a scan of your face’. We also made sure to clarify why we needed certain information from our users. We also improved usability by removing collapsed content so text was easier to read, and added a contact form on our data privacy screen, which we hope will reassure and encourage younger users to ask any questions they may have about how their personal data is being handled. Communicating with our younger users by improving readability Where comprehension is involved, it’s incredibly important that our younger users understand our services as best they can. To do that, we need to make sure our wording is easy to read. We used a number of readability tools to help the editing process. Hemingway helped us to pinpoint the key areas of improvement. Before edits After edits Once we made the edits, we ran our new and improved content through Story Toolz to see how much easier our content was to read using seven different readability indices. We made sure that in as many circumstances as possible we were improving the way our services could be understood by young people. FAQs If we want children to understand how they can use the app, it’s important that our FAQs are approachable and accessible. We hope that by doing this, we become as transparent as possible in line with the Code’s fourth standard. On average, we improved the readability of our FAQs by two school years by using less words and using simpler alternatives to complex terms. We hope that children will feel more comfortable navigating our app when they have questions about how to use it. Customer Service Emails We made our email templates even easier to read, all of which now have a readability grade of 5 or below. That’s a reading age of 10 years old. Making our privacy information easier to understand Bite-size summaries We’ve added bite-sized summaries to sections of our key privacy and terms documents. We initially thought about calling these blue boxes, but quickly realised this wouldn’t be accessible to people with visual impairments. Instead, we decided to include an information icon and refer to the summaries as information boxes. Definitions We have added a section on definitions that explains frequently used key terms in our privacy information, such as “third parties” and “biometrics”. Privacy notice for children and young adults We’ve written a simplified privacy policy for children and young adults. Rather than add a definitions section, we decided to find alternative words altogether and write a summary with the key information about how we do privacy at Yoti. This is not a substitute for our detailed privacy policy but it allows users to understand privacy in a more simplistic way. We’re also designing a new structure for our privacy pages to make them easier to navigate. There’s a fixed sub menu that shows an overview of all sub-pages and we clearly signpost to key pages based on whether you’re an end user, corporate client or young adult. Our products evolve with child safety requirements The efforts don’t stop there. We hope to continually improve our services for children over the coming months and years. Since reviewing our existing app onboarding and other flows, we are planning to make some changes which will be included in our next few releases. So watch this space. While we continue to act in the interest of our users, we encourage all businesses that are affected by the Code to act with us and create safer spaces for children. If you would like to find out how we can help you and your business to comply with the Age Appropriate Design Code, get in touch with us today.
Making it easier for EU residents to prove their COVID-19 Vaccination status
Vaccine certificates are proving fundamental in safely opening the world up, and being able to prove your COVID status via the Yoti app for travel, leisure and work has been the most requested feature by the Yoti community in recent months. That’s why we’re excited to announce that it is now possible for fully vaccinated people to add their EU COVID-19 Vaccine Certificate to their Yoti app. Add your vaccine certificate to the Yoti app in seconds Before you add your vaccine credentials to your Yoti app, you’ll need to make sure you’ve also added your ID first. This is because we want to make sure that your information is verifiable and trusted. Then when you add your vaccine certificate, we match it with your verified identity information to make sure it’s definitely yours. And, it’s all securely stored and encrypted in your Yoti account which only you can access. Showing your vaccine certificate is easy and simple. You can either show your QR code upon request, or share it digitally if you need to prove your vaccine status online. So, next time you’re heading into a bar, restaurant or stadium that requires you to prove your vaccination status, just show your phone. Once you’ve added your ID document, it’s simple: Add your certificate on the ‘Personal details’ page on the Yoti app. When entering a venue, simply open your vaccine certificate card on the ‘My Yoti’ page and show the QR code. The person checking your details will scan your QR code to check that your certificate is real. This is the latest step in helping people do the things they love safely again. If you haven’t already, download the Yoti app today.
Tackling child sexual abuse online with the Safety Tech Challenge Fund
We’re delighted to announce that the Safety Tech Challenge Fund 2021 has awarded Yoti and our collaborators with not one, but two rounds of funding. Working in partnership with Galaxkey & Image Analyzer and DragonflAI, we are looking to tackle child sexual abuse and demonstrate how end-to-end encryption and AI-powered image analysis could be used to create secure solutions that protects young people online. Between 2019 and 2020, over 10,000 cases of online child sexual abuse were reported to police forces across the UK. In efforts to create change to prevent such crimes, the UK Government created The Safety Tech Challenge Fund. It is a progamme that supports the development of innovative technologies to help provide better protection to victims of child sexual abuse. Led by the DCMS and Home Office, winners have been awarded with £85,000 for their proposals. Yoti is delighted to be: 1. Partnering with Galaxkey & Image Analyzer to create an end-to-end secure messaging platform End-to-end email encryption platform, Galaxkey has partnered with Yoti and content analysis platform Image Analyzer to innovate a messaging platform that detects explicit content before it is sent, rather than after the fact. The tech would work by creating an encrypted messaging platform that allows the user to verify their age using Yoti’s facial age estimation or the Yoti digital ID app when they create an account. Any messages sent via the platform will go through an explicit content detection process using Image Analyzer’s AI to prevent explicit material from being sent to a recipient. The solution is also expected to evolve beyond images in the future, scanning voice, text and URLs. We hope this will provide even more protection against explicit content. Upon detection, the content would be sent to the reporting server on Galaxkey’s NCSC accredited encrypted workspace platform for moderation. By creating a working platform which can detect, action and report explicit content prior to delivery of the content to a recipient, we hope to prevent child sexual abuse material from being sent via messaging platforms. 2. Working with DragonflAI to detect and flag child sexual content on a device We’ve also joined forces with video and image moderation company DragonflAI to create a solution that instantly detects a person’s age in explicit content on a device and completely offline. Specialising in the detection of nudity, DragonflAI’s algorithm has a success rate of 97.9%. Combined with Yoti’s age estimation technology, the collaboration will be able to detect the ages of people involved in explicit content. This will then allow successful moderation of illegal content without a third-party being involved. The goal of this collaboration is to create a tool that can detect unseen and new indecent images with a high degree of accuracy without the content leaving a device. We are proud to be putting our solutions forward to encourage innovation, helping change the digital space to better protect children online. We thank the Safety Tech Challenge Fund for welcoming the use of tech to tackle the rise in online-linked sexual crimes, and look forward to working with our partners to create tools that make the internet a safer place for children.
Protect yourself and your pets with Post Office EasyID and Yoti peer-to-peer checks
Scammers delight with fake online profiles Identity-related fraud is accelerating in the real world and particularly online, where it’s easy to hide and act behind a fake profile unchecked. Despite calls from victims and campaigners, most platforms don’t want to add friction into their user journeys in fear that people will migrate to another site. Fraud comes in a number of shapes and sizes, and the consequences can be physically, financially, and emotionally damaging. Whether someone is trying to sell stolen goods, committing romance scams, catfishing, or advertising property rentals that don’t exist, there are a whole host of fraud-related crimes and identity is often at the centre of it. The problem continues to grow. But, you can complete your own checks with Yoti and Post Office EasyID. Catch a catfish with peer-to-peer checks There is a solution if your platform of choice doesn’t ask people to prove that they are who they say they are. Anyone with the Yoti or EasyID app can swap their verified details with another person and be confident about who they are dealing with. It’s free and can be done in seconds. We created peer-to-peer checks to provide a versatile solution to build trust, transparency and improve online and face-to-face safety, one that you control. From people to pets, everyone is impacted We recently met Johnathan and Piotr from Creslow Corgis, who are 5 Star Licensed, Kennel Club Assured Breeders of Welsh Pembroke Corgis, wanted to protect themselves, their customers and their furry family members from the rising threat of dog-related crime. An estimated 2,000 dogs are reported as stolen each year in England and Wales. So, if you’re looking to buy a pet, how can you be sure that the breeders are legitimate and aren’t operating an illegal dog breeding business? Johnathan, Creslow Corgis: “The health, wellbeing, welfare and security of our dogs and pups is always our top priority. Demand for pups is soaring. And everyone wants their own Instagram star. This isn’t a good thing for the industry. Fraud and theft are increasing with rogue breeders, and puppy thefts from homes. People literally walking in and taking puppies from their families, days or even weeks old. It’s really quite scary when you think about it.” Well, that’s why Johnathan and Piotr use peer-to-peer checks. First of all, they can be sure that the customers are who they say they are and give the corgis a loving forever home. But also, customers can put their trust in the breeders, all the same, knowing that they haven’t lied about their identity. Johnathan, Creslow Corgis: “Over the years we’ve had to adapt our vetting process to improve security and protection. We need to be as confident as we can that the people we’re letting into our home are the right people. In a nutshell, for breeders and buyers alike, we all need to know who we’re dealing with. We needed to find a trusted, secure solution. It had to be affordable for small businesses like us.” The digital ID app is free, reusable, and privacy-preserving. So, if you request that someone share their details with you and they refuse, you might be better off taking your business elsewhere. Johnathan, Creslow Corgis: “We discovered Post Office EasyID and for us it’s the perfect solution. It gives us the assurance that people are who they say they are, whether you’re selling or buying a puppy or whether you’re putting your dog in daycare. So for us it’s a win, for our customers a win, and for our dogs and puppies it’s really a win.” EasyID - Swap verified details with buyers or sellers in seconds from Yoti Bill Lambert, spokesperson for The Kennel Club said “When buying a puppy, we always urge potential owners to conduct thorough research, and this includes making sure the breeder is a responsible and reputable source for buying their puppy from. Likewise, the breeder should be carrying out similar steps to find out as much about the purchaser that they can, so they have peace of mind that the buyer is genuine and that the pups are going to a permanent, loving home. Not only does this approach help to ensure that the puppy is well-bred, happy and healthy, but also minimises the risks of encountering scams and heartbreak.” Sounds too good to be true? Whether it’s buying and selling or dating and meeting, a peer-to-peer swap can save you emotional and financial pain and wasted time. It gives you the option to swap only the necessary information, so you don’t need to share more than you are comfortable with – unlike sending a copy of your ID, which could open you up to more fraud risks. Perfect for small businesses For a small business user, it’s the perfect way to gain and earn trust with customers. Paperwork free and cost-effective, you will save time on administrative processes in a way that is GDPR-aligned. What’s more, the tool comes from the Post Office brand that people across the UK widely trust. How it works Open the EasyID app. Tap Share and select the details you’d like to swap or share, like your photo or full name. Choose how to swap your details (via text, email or face to face). Once the other person has approved your request to swap details, you’ll get the exact same details from them. Do you know anyone affected by a scam that could have been prevented with our peer-to-peer checks? We’d love to hear from you to help fight fraud together.
Yoti approved to commence accreditation as a private digital identity provider under the Australian Government’s Trusted Digital Identity Framework
We have now been approved to commence accreditation as an identity provider under the Australian Government’s Trusted Digital Identity Framework (TDIF). The stringent accreditation process has already begun to validate the Yoti app and embedded ID verification platform under the TDIF accreditation standards. Accreditation will enable us to perform digital identity transactions to relying parties and verify individuals to a high level of trust. Trusted Digital Identity Framework: making space for digital ID As part of Australia’s drive to be a leading digital economy by 2030, the Australian Government Digital Identity System – led by the Digital Transformation Agency (DTA) – is transforming the way people do business; merging the physical and digital worlds to transform every aspect of life. This benefits both businesses and consumers, driving growth by connecting traditional industries with emerging technologies. It’s important to build trust when it comes to the safety and security of personal information. The TDIF accreditation ensures people and businesses have confidence in personal data usage, boosted by convenient ways for Australians to prove their identity online – with robust solutions like the free Yoti app. In order to become a TDIF accredited provider, applicants are required to demonstrate how their Digital Identity service meets requirements for: accessibility and usability privacy protection security and fraud control risk management technical integrity, and more. The TDIF defines the standards, rules and guidelines for applicants that can operate as digital identity providers. At Yoti, we will demonstrate the TDIF obligations by undergoing annual assessments against consumer protection, privacy and data protection for state and territory government structures – aimed at building safeguards that protect Australians and businesses alike. Secure, safe and reusable ID Our AI-powered technology and digital ID app will deliver a seamless identity verification solution for online and real-world businesses in Australia. The free app is a safe and highly secure place to store personal details, which are encrypted and under the owner’s control. Designed to make it simpler and safer to prove who they are online and in-person, people can choose to add their identity documents and facial biometrics to their Yoti app. In just a few minutes, they will have a verified, reusable digital ID that protects their details and allows them to share them with others quickly and securely. With Yoti, people no longer have to copy, send and share their ID documents, and businesses can be confident customers are who they say they are. It’s a privacy-preserving solution to outdated online identity verification methods. Built with data minimisation at its core, people can share specific identity details without revealing their full identity using the Yoti app, protecting their privacy and empowering personal data ownership and tackling ID fraud with verified information. Tap into the existing network of over 10 million app downloads worldwide. Darren Pollard, Regional Director, Yoti Australia said, “Yoti is both proud and excited to begin its accreditation under the TDIF, and we look forward to working closely with the team at the DTA. We are confident that the global Yoti digital identity platform will meet the requirements of the TDIF. Many private and government organisations around the world have already put their trust in Yoti for digital identity proofing and we wholeheartedly support the approach by the Australian government to create a national framework for digital identity providers to ensure public confidence. As more state and federal government agencies look to rely on the TDIF standard for regulations around identity verification, Yoti looks forward to offering our platform to millions of consumers and thousands of Australian businesses, big and small. This is another vital step in our commitment to building partnerships and solutions that will help transform the digital identity landscape in Australia – and follows our recent announcement with eftpos’ connectID to deliver trials to support the legislative changes introduced by the New South Wales Government that require digital age verification for online liquor sales beginning in June 2022.” To hear more about what we’re up to in Australia, contact us here to get in touch.