TechBytes with Philipp Pointner, Chief Product Officer at Jumio

Could you tell us about your role and the team/technology you handle at Jumio?

I serve as a Chief Product Officer at Jumio, the leading provider of online identity verification technology and biometric-based authentication services for financial services, travel, sharing economy, gaming and cryptocurrency sectors. A product visionary and leader in the global financial services and e-commerce spaces, I have successfully led products for over a decade.

How does Identity Authentication technology work for Marketing and Digital Advertising?

Biometric-based identity verification and authentication plays an important role in just about any industry, but especially those industries where important information and data is transacted online.

Increasingly, Digital Marketing agencies want to more definitively assess the identities of new online customers — that is, verify that a new online customer is who they claim to be. Jumio helps our Digital Marketing customers quickly and securely verify new customers. We do this by requiring their end-users (new users to their platform) to take a picture of their government-issued ID (e.g., driver’s license) which is then corroborated with a selfie-and liveness detection (to ensure the user is not attempting to spoof the system). Unnecessarily long and complicated ID checks, such as knowledge-based authentication (KBA) and credit bureau lookups are no longer very secure or considered best practices by Gartner and NIST.

These inefficient methods sometimes require customers to visit a branch office and spend a significant amount of their free time finding proof of address and their passport, heading into town, queueing, and finally verifying their identity. Jumio helps streamline the whole process (it takes less than 60 seconds on average) and is significantly more reliable and secure than traditional identity proofing methods.

What is the engine driving your IA platform? How does AI and Machine Learning fit into your product capabilities?

The biggest enabler for our ML and AI efforts is the volume of data we see coming through our services. In the ML world it isn’t the best model that wins, but the best data to train the model.

We use ML to replace tasks that traditionally would have been executed by a human. Having the ability to perform those tasks with AI helps us shape products that are infinitely more scalable with better user experience, higher conversion rates, and repeatable, predictable outcomes.

What differentiates Jumio’s AI capabilities in fighting deepfakes? Which other technologies are currently used to identify deepfakes – and why they are reliable/unreliable?

As part of the Jumio identity verification process, we have embedded certified liveness detection into our new Jumio Go offering (but it’s also part of our core identity verification solutions). Liveness detection prevents bots and bad actors from using photos, videos, masks or other biometric data (stolen or otherwise) to create or access online accounts. Liveness ensures only real humans can create and access accounts.

Sometimes liveness detection methodologies ask users to blink, smile, turn/nod, watch colored flashing lights, make random faces, speak random numbers and much more. Sadly, most of these legacy techniques are easily spoofed by deepfakes.

Enter, certified 3D liveness detection.

In the world of liveness detection, there is a large distinction between certified and uncertified methods. Certification testing is performed by iBeta, a NIST/NVLAP-accredited lab, based in Denver. They are currently the only lab performing presentation attack detection (PAD) testing guided by the all-important ISO 30107 global standard.

In fact, Jumio is proud to have partnered with FaceTec, which recently received perfect scores in testing guided by the ISO 30107 biometric standard. FaceTec is the first and only biometric technology to achieve perfect results in Level-1 and Level-2 certification testing. This is noteworthy because the Level-2 test attempts to spoof the technology even using live human test subjects wearing realistic 3D masks.

What are your predictions on the future of AI? How can digital advertisers and publishers safeguard their interests from dramatic shake-ups in the industry as a result of data privacy and security standards?

At Jumio, we’re investing heavily in AI. Last year, we launched Jumio AI Labs in Montreal, a subsidiary dedicated to the creation, experimentation and at-scale deployment of Machine Learning and Deep Learning technologies. The Montreal office expands upon the innovation driven by Jumio’s Vienna-based AI team by building production models that perform three vital functions related to online identity verification: data extraction, fraud detection, and risk scoring.

While Big Data is important, you also need to have the data intelligently tagged. At Jumio, we’ve hired qualified verification experts and AI trainers to tag ID documents — both good and rejected images — and to help train our ML algorithms. Image tagging is based on answering the following questions:

• Was the image scuffed?
• Was the ID hole punched?
• Which country was the ID from?
• Was there glare?
• Was part of the picture obscured by a thumb?

By tagging tens of thousands of IDs in this manner, the algorithms that feed machine learning get smarter, faster and learn how to recognize these patterns automatically. We’re also using our AI models to flag areas on the ID that require closer inspection — these could be areas of high glare or suspect fonts that may not match the ID template. Jumio’s AI models are helping our verification experts focus their attention to help make the best verification speed, while also speeding up the verification process.