FB pixel

Dataset generating model boosts biometric performance and privacy, researchers say

Dataset generating model boosts biometric performance and privacy, researchers say

It is possible to create synthetic samples for facial recognition algorithms that simultaneously maintain code performance and cut privacy leakage, according to an international team of researchers.

The scientists created a two-stage framework they have named FaceMAE because it uses masked autoencoders, or MAEs. It is divided in two – the biometric training and deployment stages. Their work has been published, but not reviewed.

The headline here is that as it generates faces for use as training data, FaceMAE considers face privacy and recognition performance simultaneously, report researchers from the National University of Singapore; University of Edinburgh, Scotland; Tsinghua University, China; and InsightFace, an open-source two- and three-dimensional face analysis library.

The results are encouraging. FaceMAE cuts privacy leakage by about 20 percent. It reduced the error rate by 50 percent compared to the next-best performing method when it was trained on reconstructed images from three-quarter masked faces of the Casia-WebFace dataset.

Synthetic face biometric data generated for algorithm training is already drawing millions in investment, so a method achieving similar privacy protection with better accuracy would be in demand.

FaceMAE’s leak risk was measured based on face retrieval between reconstructed and original datasets. The team’s experiments indicate that the identities of reconstructed images are difficult to retrieve.

A technical summary of the paper can be found on the machine-learning news site Marktechpost.

Article Topics

 |   |   |   |   |   | 

Latest Biometrics News


Age verification comes to social media as age of unregulated use nears an end

If trends continue, social media is set to follow in the path of cigarettes: an activity benefitting early from lax…


AI can save UK govt £40B annually, transform public services: Blair Institute

AI will soon be used to pre-check applications for correct information, triage cases by calculating complexity and routing them appropriately,…


Papua New Guinea completes national data protection and governance policy

The Ministry of Information and Communications Technology has announced the completion of the national data protection and governance policy, marking…


Interpol issues call for biometrics firm to provide mobile data collection devices

Interpol has issued a tender for mobile ​​biometric collection (MBC) devices for collecting fingerprints and facial images. Specifically, the project…


ICE, CBP sued for details on migrant data sharing agreements

Digital rights advocacy group Access Now is suing the U.S. Customs and Border Protection (CBP) and Immigration and Customs Enforcement…


French travel minister joins UK lawmakers in floating EES postponement

The European Union’s biometrics-based travel scheme is raising concern in France with the local transport minister not excluding postponement. Minister…


Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Read This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events