How to spot a deepfake: Scientists say it’s all in the glimmer of the eyes

Input, The Next Web and other tech-focused outlets reported that a team led by Siwei Lyu, SUNY Empire Innovation Professor in the Department of Computer Science and Engineering, has created a system for detecting deepfakes, or highly realistic images of people that are generated by computers and hard to discern from real faces.

The new method is "remarkably simple," Input reports: The researchers' new tool looks at how light is reflected in the eyes. The cornea has a mirror-like surface that creates reflective patterns when looking towards a light source. The reflection is usually similar in both eyes because they’re seeing the same thing. Deepfake programs struggle with the reflections of eyes, often displaying inconsistencies like a mismatch in the locations of the reflections where they should be the same in both eyes. 

Read the stories here: Input and The Next Web.