DNA facial prediction could make protecting your privacy more difficult

3 May 2018

Dr Caitlin Curtis and Dr James Hereward, The University of Queensland

Everywhere we go we leave behind bits of DNA.

We can already use this DNA to predict some traits, such as eye, skin and hair colour. Soon it may be possible to accurately reconstruct your whole face from these traces.

This is the world of “DNA phenotyping” – reconstructing physical features from genetic data. Research studies and companies like 23andMe sometimes share genetic data that has been “anonymised” by removing names. But can we ensure its privacy if we can predict the face of its owner?

Here’s where the science is now, and where it could go in the future.

Predicting hair, eye and skin colour

DNA phenotyping has been an active area of research by academics for several years now. Forensic biology researchers Manfred Kayser and Susan Walsh, among others, have pioneered several DNA phenotyping methods for forensics.

In 2010, they developed the IrisPlex system, which uses six DNA markers to determine whether someone has blue or brown eyes. In 2012, additional markers were included to predict hair colour. Last year the group added skin colour. These tests have been made available via a website and anyone who has access to their genetic data can try it out.

Trait predictions are being used to address a number of questions. Recently, for example, they were used to suggest that the “Cheddar Man” (the UK’s oldest complete human skeleton) may have had dark or dark to black skin and blue/green eyes. The predictive models are mostly built on modern European populations, so caution may be required when applying the tests to other (especially ancient) populations.

The full picture

Research on DNA phenotyping has advanced rapidly in the last year with the application of machine learning approaches, but the extent of our current capabilities is still hotly debated.

Last year, researchers from American geneticist Craig Venter’s company Human Longevity, made detailed measurements of the physical attributes of around 1,000 people. Whole genomes (our complete genetic code) were sequenced and the data combined to make models that predict 3D facial structure, voice, biological age, height, weight, body mass index, eye colour and skin colour.

The study received strong backlash from a number of prominent scientists, including Yaniv Erlich, aka the “genome hacker”. The study seemed to predict average faces based on sex and ancestry, rather than specific faces of individuals. The method of judging the predictions on small ethnically mixed cohorts was also criticised.

Even with accurate facial predictions, Erlich noted that for this approach to identify someone in the real world:

an adversary … would have to create [a] population scale database that includes height, face morphology, digital voice signatures and demographic data of every person they want to identify.

Because without a detailed biometric database you can’t get from the physical predictions to a name.

A database to match?

It turns out that the Australian government is in the process of building such a database. “The Capability” is a proposed biometric and facial recognition system that will match CCTV footage to information from passports and driving licences. Initially billed as a counter-terrorism measure, there are already reports the service may be provided for a fee to corporations.

At the same time, the Australian Tax Office has just initiated a voice recognition service. It’s easy to imagine how this kind of system could be integrated with “The Capability”.

And it’s not only Australia establishing the capability to become a biometric, face-recognising surveillance state. India is deploying the Aadhar system, and China leads the world in facial recognition.

Dr Caitlin Curtis, Research fellow, Centre for Policy Futures (Genomics), The University of Queensland

Dr James Hereward, Postdoctoral Research Fellow, School of Biological Sciences, Faculty of Science, The University of Queensland

This article was originally published on The Conversation. Read the original article.