Webinar to unmask the threat of video deepfakes and biometric injection attacks

Video injection attacks used to deliver deepfakes are the top emerging threat to fraud prevention systems around the world in 2024. In an upcoming webinar hosted by Biometric Update and ID R&D, company President Alexey Khitrov will explain the challenge posed by video deepfakes, and how they can be mitigated.

Register now for this webinar

The use of deepfakes presents a major challenge to biometric security systems, particularly those using facial recognition technology. With the ability to replicate someone’s appearance and movements, synthetic identities can be created to gain unauthorized access to sensitive information.

Two types of attacks can be carried out using non-live facial representations – injection attacks and the more widely-known presentation attacks. In presentation attacks, non-live representations such as photos, videos, or 3D masks are used to trick the biometric system into recognizing them as live input. Injection attacks are more sophisticated and involve manipulating the biometric system’s data processing or capture mechanism, such as hacking the software or hardware to inject pre-recorded images or videos as live input.

These attacks can be levied against user onboarding, account opening and KYC systems, but also live video calls and video-conferences.

Detecting deepfakes is increasingly difficult for both people and automated systems, ID R&D says.

“While regular deepfake detectors achieve an accuracy of about 90%, I’m proud our engineers have combined ‘Deepfake Detection’ plus ‘PAD’ plus ‘Injection Attack Detection,’ achieving an amazing near 100 percent accuracy in FaceSwap detection,” says Konstantin Simonchik, chief scientific officer and co-founder at ID R&D in a LinkedIn post.

During the webinar, attendees will have the opportunity to learn about the new IDLive Face Plus, which offers advanced detection capabilities to safeguard against both presentation and injection attacks. This system is highly effective in identifying a wide range of attack types, with high accuracy and a low rate of false positives, according to ID R&D.

Learn more about the latest attack types against biometric security systems and how they can be prevented by registering for this free webinar.

Article Topics

biometric liveness detection  |  biometrics  |  deepfake detection  |  ID R&D  |  injection attacks  |  webinar