People 'n' Issues

UJ raises identification bar

June 23rd, 2017
A company established as a joint venture by the University of Johannesburg, has developed identification technology that simulates human cognition – and it works off a smart phone.
ai_shutterstock_360442685

The company,  aiThenticate Computervision Labs, has developed a technology called aiDX to answer one of the most difficult, challenging and urgent questions of our time: “Who is someone… actually?

Says André Immelman, CEO of aiThenticate Computervisio Lads, “With identity theft now representing the foremost white collar crime in the world – fuelled largely by the exponential growth in mobile communications – the technology has been engineered as the next generation authentication technology.”

The failure of conventional authentication methods such as signature, identity artefacts, passwords, and PINs, to effectively arrest identity theft, has seen a rapid shift towards biometrics means of authenticating a person. These include fingerprints, faceprints, voiceprints, and irisprints.

“Last year, the global loss from identity theft was about $2-trillion, and it is doubling every year,” says Immelman. “In South Africa alone, R1-billion was lost in SIM card swaps last year. These figures go to show just how ineffective conventional biometrics are in the post-9/11 world, where someone sitting at his PC in one country is able to hack into a bank account in another country, even on a completely different continent.

“Conventional biometrics are based on simple geometry: connecting key features to form a pattern that is then associated with a particular individual. It’s a bit like a child’s game of ‘connect the dots’ to form a picture. However, while conventional biometrics may be sufficient for the purposes of unlocking a smart phone, the scarcity of key features that are generally visible in a latent fingerprint or a faceprint, for example, means that this system tends to fail rapidly with larger population groups.

“The simple mathematics that underscore conventional biometrics explains why misidentification is a very real problem with fingerprint, faceprint, voiceprint and irisprint solutions, rendering conventional biometrics inadequate as a real-world authentication solution.”

For that reason, aiThenticate Computervision Labs turned to “deep science” for an answer to the all-important “Who?” question. Using proprietary algorithms that simulate human cognition, aiThenticate computervision scientists – who analyse digital images – have successfully managed to develop the next generation of authentication technologies.

“The human brain simply operates at a much deeper, far more advanced level than what is possible with conventional authentication methods. Extensive field tests have shown that, as the next generation authentication technology, aiDX eclipses, and in fact, surpasses the overall performance of conventional authentication methods by a factor of some 20x on average*.”

Making the technology universally accessible, aiDX can be deployed on any device that’s equipped with a digital camera, including the one device we all carry with us all the time: a standard, off-the-shelf Android or iOS smartphone or tablet.

“aiDX makes it possible to do what conventional authentication methods are simply not able to do under the rigours of real-world conditions: answer the ‘who’ question accurately and conveniently,” says Immelman.

“We anticipate that it will have applications in a wide variety of industries and market sectors, including financial services, access control, identity management, e-commerce, authorisations, grants, law enforcement, and much more – in fact any situation where the ‘who’ question is fundamentally important.”

Leave a Reply

Your email address will not be published. Required fields are marked *


6 × 3 =