Fighting the Fakes: Data scientists create cutting-edge tool to verify image authenticity
York St John University-led research is “essential in helping people to navigate the fine line between reality and fabrication”
Data scientists at York St John University have announced the launch of a pioneering new tool to spot fake images.
Pixelator v2 uses a new combination of image veracity techniques with capability beyond what can be seen by the human eye. It can identify subtle differences in images with greater accuracy than traditional methods and has been shown to detect alternations as small as 1 pixel in size.
The tool was developed by York St John University’s Data Science academics, supported by colleagues from the University of Essex and software developers at Nosh Technologies. It aims to revolutionise the way we compare and analyse images for cybersecurity purposes.
It is now available for free at GitHub, with the research underpinning the innovation published in the peer-reviewed Electronics journal. Read the paper.
Pixelator v2 is designed to support those with the greatest need for accuracy and the team say the software will be of particular use to cybersecurity professionals, analysts and researchers. It employs an advanced method that combines:
– LAB Colour Space Analysis: A perceptual colour model that mimics human vision, allowing the tool to detect differences in images that may not be immediately visible to the naked eye.
– Sobel Edge Detection: A technique that highlights structural variations in images, such as changes in edges and boundaries.
With the rise of Generative Artificial Intelligence (AI) tools capable of creating hyper-realistic images, distinguishing between real and AI-generated content has become increasingly challenging. Pixelator v2 is a significant step towards addressing this issue. By enhancing our understanding of how images differ perceptually, the tool lays the groundwork for future projects, focused on detecting or predicting AI-generated images—critical for combating misinformation and ensuring digital trust.
The research team is actively working on the next phase of this project, extending Pixelator v2 to directly detect and predict generative AI-created images. This ongoing development aims to equip users with advanced tools to navigate an increasingly AI-driven digital landscape.
Dr Somdip Dey, lead researcher on the project and Lecturer in Data Science at York St John University, said:
“In an era where images dominate communication, the ability to understand visual authenticity has never been more critical.
“This tool is a stepping stone towards a broader mission—developing technology to detect and predict AI-generated fake images.
“As generative AI becomes more widespread, tools like Pixelator v2 are essential in helping consumers and professionals navigate the fine line between reality and fabrication.”
This project was made possible through collaboration between experts across academia and industry:
– York St John University: Dr Somdip Dey, Dr Jabir Al-Ani, Dr Sam Hill, and Dr Julian Thompson.
– University of Essex: Dr Aikaterini Bourazeri.
– Nosh Technologies: Suman Saha and Rohit Purkait.
Dr Somdip Dey will be presenting the research findings from this project at the AI Summit of Black Hat Europe 2024 conference on 10 December in London.
Researchers and professionals are encouraged to explore Pixelator v2 and its applications in image security and analysis. Access the software at GitHub https://github.com/somdipdey/Pixelator-View-v2/tree/main