FB pixel

Deepfakes advance from enough heart for romance scams to thwarting detection

Corporate leaders can turn to BlackCloak if phishing passes first blush
Deepfakes advance from enough heart for romance scams to thwarting detection
 

Minute changes in skin color due to blood flow in time with heartbeats have been used to differentiate deepfakes from real videos in the past. The method now appears destined for the graveyard of deepfake detection techniques, with researchers finding generative AI can now replicate the variations caused by pulse.

Deepfake detection based on heart rate and blood flow was discussed, and a model with high accuracy shared during an EAB event in 2022.

A paper published this week in the journal Frontiers in Imaging from researchers with the Fraunhofer Institute for Telecommunications and Humboldt University, both in Berlin, started with videos of dozen people taken while their heart rate was measured with an electrocardiogram (ECG)

The “High-quality deepfakes have a heart!” researchers used remote photoplethysmography (rPPG) to analyze local blood volume changes, and found that the method produces reasonable estimates of pulse rate, as measured by the ECG. But they also found when inserting digitally altered faces that the deepfakes retained the effect of heartbeat in the videos.

Analysis of the spatial distribution of blood-flow, however, could still be useful for detecting these high-quality deepfakes.

Many phish in the sea

A criminal deepfake ring has been busted by police in South Korea after stealing $8.4 million in investment and romance scams, JoongAng Daily reports.

An investigation by the Ulsan Metropolitan Police Agency found that more than 100 people had been scammed since March, 2024. The police arrested 10 people on charges under the Act on the Aggravated Punishment of Specific Economic Crimes, and booked an additional 35 who were involved, for example as chat platform operators, without detention.

The scam operated out of Cambodia, with deepfake images and video chats. Korean authorities are now attempting to extradite the couple accused as ringleaders from Cambodia.

An article by 404 Media profiling “yahoo boys” in Nigeria includes a comment from one that he considers the deepfake and video injection technologies not ready for reliably passing KYC biometric checks, but easily good enough for romance scams.

A deepfake fraud ring was recently broken up by authorities in Hong Kong after netting over $4.3 million in romance scams.

BlackCloak launches spear-phishing shield

Florida-based BlackCloak has launched an identity verification solution specifically designed to protect  company executives from deepfakes of their trusted contacts.

The new capability is built into BlackCloak’s Digital Executive Protection Technology Platform. Platform users who receive a suspicious message through any channel can verify who it came from through the BlackCloak app, according to a company announcement. The company plays the roll of a trusted intermediary.

BlackCloak also sponsored a recent report from the Ponemon Institute showing the frequency with which corporate leaders are targeted by deepfakes, with 42 percent of organizations reporting an executive or board member has been sent a deepfake.

Related Posts

Article Topics

 |   |   |   |   |   | 

Latest Biometrics News

 

The King’s Speech signals that digital ID in the UK is a go – again

The King hath spoken: his ministers will “proceed with the introduction of Digital ID that will modernise how citizens interact…

 

Digital ID program gets $650M for expansion in Australian federal budget

The Australian government’s 2026-27 Federal Budget includes a major financial commitment to digital ID, in stating that “the Government is…

 

Age assurance industry juggles global headlines, major disruptions at 2026 GAASS

The 2026 Global Age Assurance Standards Summit marked both the arrival of age assurance onto the global main stage, and…

 

Met Police tout arrests, crime drop from permanent LFR camera pilot

The London police have published the results of the UK’s first permanent live facial recognition (LFR) test: During the six-month…

 

Alcatraz AI adds automation, alerts to facial biometric access platform

Alcatraz AI, a facial biometric authentication provider for physical access, has announced a set of platform updates that add audible…

 

Privacy fears rise in New Zealand over AI, biometric data use

A new survey shows that for New Zealanders, concerns about biometric technology and children’s online safety are now common. As…

Comments

Leave a Reply

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

Biometric Market Analysis and Buyer's Guides

Most Viewed This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events