By 2024 Almost a trivial thing The idea of using AI to create realistic images of people has gained popularity, raising concerns that such fake images might be detected. Recently Announced A new method to detect AI-generated deepfake images by analyzing human eye reflections. Royal Astronomical Society National Astronomy Meeting Last week, astronomers applied a tool they use to study galaxies to probe the consistency of light reflections in the eye.
Adejumoke Owolabi, a Masters student at the University of Hull, Dr Kevin Pimblettprofessor of astrophysics.
Their detection technique is based on a simple principle: a pair of eyes illuminated by the same set of light sources will typically have a similarly shaped set of light reflections in each eye. Many AI-generated images created to date do not take into account ocular reflections, and therefore the simulated light reflections are often inconsistent between each eye.
In a sense, astronomical perspective isn’t even necessary for this kind of deepfake detection, as a quick glance at a pair of eyes in a photo will reveal discrepancies in reflections. Portrait artist But applying astronomy tools to automatically measure and quantify deepfake eye reflections is a novel development.
Auto Discovery
At the Royal Astronomical Society blog In the article, Pimbret explained that Owolabi developed a technique to automatically detect eye reflections and compare the similarity of left and right eyes using morphological features of the reflections as indicators. Their findings revealed that deepfakes often show differences between the left and right eyes.
The research team applied methods from astronomy to quantify and compare ocular reflexes. Gini Coefficient,Normally Measuring the distribution of light in images of galaxiesevaluates the uniformity of reflectance across the eye’s pixels. A Gini value closer to 0 indicates that the light is more evenly distributed, while a Gini value closer to 1 indicates that the light is more concentrated on a single pixel.
In a post for the Royal Astronomical Society, Pimblett compared his method of measuring eye-reflection shape to a more common way of measuring galaxy shape in telescope images: “To measure a galaxy’s shape, we analyse whether it has a compact centre, whether it’s symmetrical, and how smooth it is; we analyse the distribution of light.”
The researchers also CAS parameters (concentration, asymmetry, smoothness), another tool in astronomy to measure the distribution of light in galaxies. However, this method has proven to be less effective in identifying false eyes.
Detection Arms Race
While eye reflex technology is a potential way to detect AI-generated images, this method may not work if AI models evolve to incorporate physically accurate eye reflexes, perhaps applied as a next step after image generation. Also, the technology requires a clear and close view of the eye to work.
This approach also runs the risk of generating false positives as eye reflections may mismatch even in real photos due to different lighting conditions or post-processing techniques.However, analyzing eye reflections may still be a useful tool in a larger deepfake detection toolset that also considers other factors such as hair texture, anatomical structure, skin details, and background consistency.
Although the technique shows promise in the short term, Dr Pimbret warned that it is not perfect: “There will be false positives and false negatives, and it won’t catch everything,” he told the Royal Astronomical Society. “But this method provides a basis, a plan of attack, in the arms race to detect deepfakes.”
