Mastering Deepfake Detection: A Cutting-Edge Approach to Distinguish GAN and Diffusion-Model Images







Luca Guarnera1, Oliver Giudice2, Sebastiano Battiato1
1 Department of Mathematics and Computer Science, University of Catania, Italy
2 Bank of Italy, Applied Research Team, Rome, Italy
luca.guarnera@unict.it, giudice@dmi.unict.it, battiato@dmi.unict.it

ACM Transactions on Multimedia Computing, Communications, and Applications









[RELATED WORKS]





Detailed Sketch of the Proposed Hierarchical Approach The input image I is first analyzed by model EL1 at level 1 (a).
Only in the case where I is classified as generated by AI (cL1 = "AI"), the image is analyzed by EL2 in level 2 (b).
Thus, if cL2 = "GAN", then I is analyzed by EL3-GAN: cL3-GAN = EL3-GAN(I) (c) otherwise
cL3-DM = EL3-DM(I) (d) in order to identify the specific architecture used for creating the deepfakes.



ABSTRACT


Detecting and recognizing deepfakes is a pressing issue in the digital age. In this study, we first collected a dataset of pristine images and fake ones properly generated by nine different Generative Adversarial Network (GAN) architectures and four Diffusion Models (DM). The dataset contained a total of 83,000 images, with equal distribution between the real and deepfake data. Then, to address different deepfake detection and recognition tasks, we proposed a hierarchical multi-level approach. At the first level, we classified real images from AI-generated ones. At the second level, we distinguished between images generated by GANs and DMs. At the third level (composed of two additional sub-levels), we recognized the specific GAN and DM architectures used to generate the synthetic data. Experimental results demonstrated that our approach achieved more than 97% classification accuracy, outperforming existing state-of-the-art methods. The models obtained in the different levels turn out to be robust to various attacks such as JPEG compression (with different quality factor values) and resize (and others), demonstrating that the framework can be used and applied in real-world contexts (such as the analysis of multimedia data shared in the various social platforms) for support even in forensic investigations in order to counter the illicit use of these powerful and modern generative models. We are able to identify the specific GAN and DM architecture used to generate the image, which is critical in tracking down the source of the deepfake. Our hierarchical multi-level approach to deepfake detection and recognition shows promising results in identifying deepfakes allowing focus on underlying task by improving (about on the average) standard multiclass flat detection systems. The proposed method has the potential to enhance the performance of deepfake detection systems, aid in the fight against the spread of fake images, and safeguard the authenticity of digital media.






Download Paper  

Cite:
@article{guarnera2024mastering,
   title={Mastering Deepfake Detection: A Cutting-edge Approach to Distinguish GAN and Diffusion-Model images},
   author={Guarnera, Luca and Giudice, Oliver and Battiato, Sebastiano},
   journal={ACM Transactions on Multimedia Computing, Communications and Applications},
   year={2024},
   publisher = {Association for Computing Machinery},
   address = {New York, NY, USA},
   issn = {1551-6857},
   url = {https://doi.org/10.1145/3652027},
   doi = {10.1145/3652027}
}





[RELATED WORKS]