Skip to main content

On the detection of synthetic images generated by diffusion models

Riccardo Corvi (University Federico II of Naples); Davide Cozzolino (University Federico II of Naples); Giada Zingarini (University Federico II of Naples); GIovanni Poggi (University Federico II of Naples); Koki Nagano (NVIDIA); Luisa Verdoliva (University Federico II of Naples)

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
08 Jun 2023

Over the past decade, there has been tremendous progress in creating synthetic media, mainly thanks to the development of powerful methods based on generative adversarial networks (GAN). Very recently, methods based on diffusion models (DM) have been gaining the spotlight. In addition to providing an impressive level of photorealism, they enable the creation of text-based visual content, opening up new and exciting opportunities in many different application fields, from arts to video games. On the other hand, this property is an additional asset in the hands of malicious users, who can generate and distribute fake media perfectly adapted to their attacks, posing new challenges to the media forensic community. With this work, we seek to understand how difficult it is to distinguish synthetic images generated by diffusion models from pristine ones and whether current state-of-the-art detectors are suitable for the task. To this end, first we expose the forensics traces left by diffusion models, then study how current detectors, developed for GAN-generated images, perform on these new synthetic images, especially in challenging social-networks scenarios involving image compression and resizing. Datasets and code will be publicly available on-line.

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00