A new partnership has been formed between Paravision and HID Global to combine the former's facial recognition and biometric liveness detection with the latter's hardware, integration, software and services. The partners plan to build enterprise-grade solutions under the HID brand for biometric access control to a range of applications across the retail, banking, air travel and healthcare sectors. The integrated solutions will offer high security with GDPR-compliant privacy protection, according to a promotional video posted to LinkedIn. Paravision President and COO Benji Hutchinson told Biometric Update in an email that the company sees the partnership with HID as a major step towards expanding its global footprint in both the public and commercial sectors. "There will be strong commercial growth as face recognition, identity, and computer vision software proliferates a number of non-traditional (outside of government sector) platforms," Hutchinson predicts.

Deepfake images and videos pose a significant threat to biometric systems used for remote identity verification, and existing liveness technologies can detect them, making an attack vector for non-deepfakes a vulnerability businesses need to be aware of. 'Why Deepfakes aren't the Real Challenge for Remote Biometrics' was presented by Ann-Kathrin Freiberg of BioID in the latest lunch talk presented by the European Association for Biometrics (EAB). More than 250 attendees from more than 40 countries around the world pre-registered for the presentation, many of whom were highly engaged in discussion throughout. The origin of the term based on the use of deep learning to manipulate or fake an image, video or audio file was reviewed, and Freiberg shared several examples of deepfakes, including a morph fake created by a BioID employee from a free app and a single image found on the internet. Some basic tips for spotting deepfake videos were shared, such as observing the transition between different areas of the face and head, and frequency or lack of blinking.

Biometric spoofing attacks are more easily spotted by artificial intelligence-based computer systems than by people, according to new research published by ID R&D. The new report, 'Human or Machine: AI Proves Best at Spotting Biometric Attacks,' compares the relative effectiveness of humans and computers detecting presentation attacks, in terms of speed and accuracy. Liveness detection was tested against images including spoof attempts with printed photos, videos, digital images, and 2D or 3D masks, according to the announcement. The company's IDLive Face accepted 0 percent of face biometric spoofs across all types of attacks and 175,000 images. People fared far worse, failing to spot spoofs in every category, including 30 percent of photo prints, one of the easiest spoof attacks for fraudsters to carry out.