Japan-based technology firm aims to improve trust in facial recognition software by making it easier to block fraud.

Anne Morris, Contributing Editor, Light Reading

September 18, 2020

3 Min Read
Fujitsu flags efforts to tackle facial recognition fraud

Efforts to develop facial recognition software by tech heavyweights such as Amazon, IBM and Microsoft have reportedly been put on hold, amid growing concerns over the way the technology views people of different races.

Although facial recognition has simplified many processes with added security, and biometric authentication is gaining in popularity, it is not without its flaws.

Indeed, software developer Allerin has already listed six potential dangers of the technology, ranging from identity fraud through to data theft, technical inaccuracies, an unclear regulatory framework, unethical use, and lack of user consent.

Figure 1: Face the truth: Facial recognition technology is mired in controversy, not least because it can have problems accurately recognizing ethnic minorities. (Source: YO! What happened to peace on Flickr CC 2.0) Face the truth: Facial recognition technology is mired in controversy, not least because it can have problems accurately recognizing ethnic minorities.
(Source: YO! What happened to peace on Flickr CC 2.0)

Fujitsu Laboratories has just revealed it is developing technology to tackle some of these problems by identifying efforts to spoof authentication systems.

The Japan-based company aims to put the technology into practical use by the end March 2021, once further improvements in accuracy have been made.

It is said to use conventional cameras to identify facial recognition fraud. According to Fujitsu, this includes impersonation attempts in which a person presents a printed photograph or an image from the Internet to a camera.

The company claims that its approach is cheaper and faster than conventional technologies that rely on devices such as near-infrared cameras to identify signs of forgery.

Instead, Fujitsu said it has developed a forgery feature extraction technology that detects the subtle differences between an authentic image and a forgery, as well as a forgery judgment technology that accounts for variations in appearance due to the capture environment.


Risk assessment
Fujitsu said such software is required because of the many risks that still remain with biometric authentication.

Credit score specialist Equifax also points to risks such as predatory marketing and stalking. The company says it may also be easier for others, like recruiters, to find out information about you that you'd rather keep private.

Want to know more about security? Check out our dedicated security channel here on Light Reading.

According to a study by Carnegie Mellon University in 2011, "when we share tagged photos of ourselves online, it becomes possible for others to link our face to our names in situations where we would normally expect anonymity."

Fujitsu said its technology is aimed at building greater trust in remote authentication in the "new normal era," without sacrificing the convenience of facial authentication.

Related posts:

— Anne Morris, contributing editor, special to Light Reading

Read more about:

Asia

About the Author(s)

Anne Morris

Contributing Editor, Light Reading

Anne Morris is a freelance journalist, editor and translator. She has been working in the telecommunications sector since 1996, when she joined the London-based team of Communications Week International as copy editor. Over the years she held the editor position at Total Telecom Online and Total Tele-com Magazine, eventually leaving to go freelance in 2010. Now living in France, she writes for a number of titles and also provides research work for analyst companies.

Subscribe and receive the latest news from the industry.
Join 62,000+ members. Yes it's completely free.

You May Also Like