World Cup: Artificially Designed Makeup Could Fool Facial Recognition Cameras

  • Camoflags wanted face paint designs to outsmart facial recognition cameras. 
  • An AI program designed the design that incorporates concepts from Juggalo makeup. 
  • The team discovered that many designs were capable of bypassing facial recognition software.

What if simple facial paint could fool some the most advanced facial recognition tools at the Qatar World Cup

Camoflags, an AI-generated Juggalo-inspired team, sought to answer this question using face paint designs that could be used for facial recognition cameras to evade facial recognition cameras.

This experiment is particularly appropriate for the World Cup as face painting is a popular feature at soccer matches, where fans show their support for their teams.

A person with red, white, and blue face paint

Face paint with the US flag stylized in Juggalo make up


The Qatar World Cup, which ends on December 18, has been criticized for its approach to security, with concerns that the event could become a hotbed for espionageVisitors could also be monitored via their phones app surveillance.

The event hasAlso been criticizedFor human rights abuses: The death of American sports journalist Grant WahlThe death of Wahl, who was on his way to the hospital following collapsing at World Cup stadium, has brought renewed attention to rights of LGBTQ people in Qatar. Wahl had been previously detained outside of the country. World Cup stadium for wearing a rainbow shirt.

About 15,000 facial recognition camerasIn and around the stadium, surveillance cameras have been placed to identify terror threats. World Cup’s chief technology officer told AFP in August.

“What you see here is a new standard, a new trend in venue operations, this is our contribution from Qatar to the world of sport. What you see here is the future of stadium operations,” Niyas AbdulrahimanTelled AFP.

Tao Thomsen is one of the Camoflags team members. project from the creative agency VirtueInsider was told by a member of the team that they came up with the idea of testing facial recognition using strange make-up combinations to distort facial features years ago as a response to the increasing popularity of deepfakes for women without their consent.The original goal of the project was create make-up looks that deepfake AI technology couldn’t recognize for women, protecting their faces against being used in sexually suggestive and non-consensual video.

A person with red and black face paint

Face paint for the Tunisian flag is stylized as Juggalo make-up


Face makeup isn’t a new idea. CV DazzleAdam Harvey’s 2010 project “” was one of the first to employ geometric shapes and other gimmicks against AI. There is also some evidence that Juggalo makeup — which consists of clown-like makeup inspired by the hip-hop group Insane Clown Posse — in particular, is effective at tricking facial-recognition systems.

Thomsen explained that the difficulty with projects like this was their practical application. It was difficult for women to wear “crazy makeup” at all times, the team realized. Soccer was different.

“Because if you can wear strange patterns on your head, it’s at the gym. [soccer] match,” Thomsen said. “People expect you will paint your team colors and flags on your face.

A person with white, red, blue and black face paint

The South Korean flag face paint is stylized as Juggalo makeup


In order to create the ideal shape, Camoflags fed an AI art software tool, Midjourney AI,A series of descriptions that would produce designs with the perfect combination of Juggalo makeup, various flags. 

Thomsen stated that they gave it descriptions and then ran the process a lot more times until we reached a result that could not be recognized as a person when it was passed through face recognition software. “And then we realized that we had some human love to clean things up and make sure that everything was in order. [the patterns]These are also aesthetic functional, as generative AI does sometimes hallucinate at times and make some really strange stuff.

The team tested the various Juggalo and flag patterned make-up on different consumer-grade facial recognition tech — the actual facial camera system used in Qatar is unknown to the public — and found many of the designs were able to elude cameras. 

The team estimates that about 80% of the 10 systems were tested were successful.

A person with green and yellow face paint

The Brazilian flag face paint is stylized as Juggalo make-up


Although Camoflags isn’t aware of any adopters of their face paint designs at the World Cup yet — and recommends people don’t risk getting in trouble in Qatar by testing its limits — they think it will help start a conversation about surveillance at sporting events.

Camoflags’ Morten Grubak, another member of the team, said that the team had created face filters that would allow users “color them out like a drawing book” by using face paint. 

Thomsen specifically mentioned the UK as a country where soccer fans love to play. have already had to dealFacial recognition technology is not working properly in sports venues around the globe. engaging in illegal activityTo. collect data for advertisements, verify ticket holders for entry at events.

Evidence also supports the assertion that facial recognition technologyis less likely than women and people of colour to correctly identify them. lead to peopleBeing misidentified by law enforcement as being involved in crimes

“We know there is a significant fraction of [soccer]We hope that facial recognition can be used to help those who have strong opinions about the subject, especially in the UK. [soccer]Thomsen asked fans worldwide to oppose facial recognition.”

Source link

[Denial of responsibility! is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – at The content will be deleted within 24 hours.]