Close this search box.

UJ-incubated research develops authentication more accurate than biometrics

aiThenticate Computervision Labs, a research-based startup residing within Resolution Circle, the technology development company of the University of Johannesburg (UJ), has developed a new ground-breaking technology that simulates human cognition.

The new technology, named aiDX, uses proprietary algorithms that simulate human cognition, far surpassing current biometric authenticators which rely on key features to form a pattern associated with a particular individual.

aiDX‘s differentiation from traditional biometric identification is its use of artificial neural networks (similar to what is being currently employed by self-driving cars).

“The human brain simply operates at a much deeper, far more advanced level than what is possible with conventional authentication methods,” said André Immelman, CEO of aiThenticate Computervision Labs.

“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 20 times on average.”

Instead of focusing specifically on a person’s key features such as in current biometric technology, aiDX uses the neural network to perform actual cognitive functions across 11 different types of identification tests, to ensure the person standing in front of it is in fact “an actual, real live person”.

Based on a sample size of some 1.4 million subjects, aiDX scored a perfect True Positive Rate (number of instances where an authentic identity is correctly identified – subject ‘A’ is determined to be ‘A’) and a perfect True Negative Rate (TNR).

As a technology built to an enterprise deployment model, aiDX securely stores all eyePrint data as ‘de-identified’ encrypted hashes either in the cloud or on-premises ( eg a bank’s own data centre), making it possible for users to be authenticated by simply referencing a central repository that can be accessed from the user’s own smartphone.

It, however, does not store the personal details of a user and no biometric information is stored on the user’s device.

Last year, the global loss from identity theft was about $2 trillion, and it is doubling every year.

In South Africa alone, R1 billion was lost in SIM card swaps last year.

“These figures go to show just how ineffective conventional biometrics is 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,” added Immelman.

Immelman said that the aiDX technology will be universally accessible, and 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.”

Concludes 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.”

Share this