• Email Us: [email protected]
  • Contact Us: +1 718 874 1545
  • Skip to main content
  • Skip to primary sidebar

Medical Market Report

  • Home
  • All Reports
  • About Us
  • Contact Us

Spotting “Stars In Their Eyes” Lets Astronomers Detect Deep Fakes

July 17, 2024 by Deborah Bloomfield

AI images are now omnipresent online. While some are absolutely ridiculous, dubbed by Gen Z and Gen Alpha as “Boomer Art”, others can fool even people paying close attention. This is particularly important when it comes to deep fakes, the made-up images of real people.

Advertisement

Counteracting the spread of these images is extremely important as they are used to spread misinformation, attack political adversaries, and violate people. A possible solution to spot the most realistic deepfakes comes from techniques used in astronomy, although astronomy borrowed it from statistics applied to wealth inequalities. It’s called the Gini Coefficient.

It is not a silver bullet but this method provides us with a basis, a plan of attack. This is an armed race. It can help now in 2024, but if we do not keep up the deepfake of 2028 will have overcome this issue.

Prof Kevin Pimbblet

Before we dive into the stats, it’s important to discuss the approach the researchers used. Machine learning algorithms that make fake images are still not good at representing reality completely. Until a few months ago, even the best ones couldn’t replicate a realistic hand and they really struggle to get the reflections you see in human eyes correctly. 

A photo of Scarlett Johansson side by side with a photo of a black man. Below a close up on their eyes. The reflection on Johansson's eyes look the same but for the fake they look different.

Both images seem real but the ‘stars in their eyes’ reveal that only Scarlett Johansson is real. The person on the right doesn’t exist.

Image Credit: Adejumoke Owolabi

Ambient light and objects are reflected in the eyes of a person photographed. The reflection in one eye is consistent with the reflection in the other, and this can be assessed statistically. The researchers do note that it is not perfect though, as the statistical analysis of the data distributions might lead to the occasional mistake.

“It is not a silver bullet.  There could be false positives or false negatives. It’s not going to get everything. But this method provides us with a basis, a plan of attack. This is an armed race. This can help now in 2024, but if we do not keep up the deepfake of 2028 will have overcome this issue,” Professor Kevin Pimbblet, from the University of Hull, told IFLScience. 

The Gini coefficient is used to estimate wealth inequality, so if a country has a dramatic difference between the wealth of rich people and the wealth of poor people, then that country – for example, the United States – will have a high Gini coefficient. But in general, the number is used to work out the inequality among the values of a frequency distribution, and that is applicable to all data, including when you want a computer to work out the morphology of a galaxy – basically, what it looks like.

Advertisement

“This is a way to analyze the morphology of galaxies. Traditionally, morphology was judged by eye. I hope it is obvious that the human eyeball is a fantastic device in a physics sense, but we are biased,” Professor Pimbblet told IFLScience. “What we really want  is an unbiased way to quantify galaxy morphology and preferably one that makes very few assumptions.”

Gini and other astronomy methods that are used in the classification of galaxies were used in this project but according to the preliminary work, only the Gini coefficient has been good enough when it comes to identifying the eyes of deep fakes.

The current research is part of a master’s project by Pimbblet’s student Adejumoke Owolabi and was presented at the National Astronomy Meeting this week. Owolabi and Pimbblet are now planning to submit a paper with the findings.   

Deborah Bloomfield
Deborah Bloomfield

Related posts:

  1. Sendoso nabs $100M as its corporate gifting platform passes 20,000 customers
  2. Delivery times for iPhone 13 stretch as COVID-19 hits Vietnam suppliers – Nikkei
  3. July Didn’t Just Set Global Heat Records, It Smashed Them
  4. Skywalker Gibbons Found In Myanmar For First Time – By Listening For Their Love Songs

Source Link: Spotting "Stars In Their Eyes" Lets Astronomers Detect Deep Fakes

Filed Under: News

Primary Sidebar

  • The “Haunting” Last Message From NASA’s Opportunity Rover, Sent From Inside A Planet-Wide Storm
  • Adorable Video Proves Not All Gorillas Hate The Rain. It Might Even Win One A Mate
  • 5,000-Year-Old Rock Art May Show One Of Ancient Egypt’s First Rulers
  • Alzheimer’s-Linked Protein Levels “20 Times Higher” In Newborn Babies – What Does This Mean?
  • Americans Were Asked If They Thought Civil War Was Coming. The Results Were Unexpected
  • Voyager 1 & 2 Could Be Detected From Almost A Light-Year Away With Our Current Technology
  • Dams Have Nudged Earth’s Poles By Over 1 Meter In The Past 200 Years
  • This Sugar Could Be A Cure For Male Pattern Baldness – And It’s Been In Our Bodies All Along
  • “Cosmic Immigrants”: Daytime Star Seen In 1604 May Be An “Alien Type Ia Supernova”
  • Ancient Meteor Crater Thought To Be World’s Oldest May Be 800 Million Years Younger Than We Realized
  • Celestial Fish And Chips And A Solar Cataclysm Shortlisted For Astronomy Photographer Of The Year
  • Tortoises Have Feelings Too, Or At Least Moods
  • What Would Happen If You Threw A Paper Airplane Out Of The ISS? New Study Finds Out
  • Tonight Will Be The Perfect Time To Witness The Moon Illusion
  • This Long-Extinct Animal Once Possessed The Sharpest Teeth On Planet Earth
  • Southwestern US Has Been Experiencing Prolonged Droughts Since The 1980s, And Now We Know Why
  • Four New Species Of Blind “Dragon Pseudoscorpions” Discovered In South Korean Caves
  • Where Are You Most Likely To Spot UFOs? We Took A Peek Inside The US’s Biggest “Alien” Sighting Database
  • “Something Unknown Is At Work Here”: Unexpected Results From NASA Mission To Deflect Asteroid
  • Dangerous Radiation Awaits Astronauts On Mars – New Mission Could Work Out Just How Much
  • Business
  • Health
  • News
  • Science
  • Technology
  • +1 718 874 1545
  • +91 78878 22626
  • [email protected]
Office Address
Prudour Pvt. Ltd. 420 Lexington Avenue Suite 300 New York City, NY 10170.

Powered by Prudour Network

Copyrights © 2025 · Medical Market Report. All Rights Reserved.

Go to mobile version