DeepFake Detection by Analyzing Convolutional Traces
By Luca Guarnera, Oliver Giudice, Sebastiano Battiato. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020
332 citations recorded by the source corpus.
The Deepfake phenomenon has become very popular nowadays thanks to the possibility to create incredibly realistic images using deep learning tools, based mainly on ad-hoc Generative Adversarial Networks (GAN). In this work we focus on the analysis of Deepfakes of human faces with the objective of creating a new detection method able to detect a forensics trace hidden in images: a sort of fingerprint left in the image generation process. The proposed technique, by means of an Expectation Maximization (EM) algorithm, extracts a set of local features specifically addressed to model the underlying convolutional generative process. Ad-hoc validation has been employed through experimental tests with naive classifiers on five different architectures (GDWCT, STARGAN, ATTGAN, STYLEGAN, STYLEGAN2) against the CELEBA dataset as ground-truth for non-fakes. Results demonstrated the effectiveness of the technique in distinguishing the different architectures and the corresponding generation process.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/3916cb5c5ead76dc3a3c126fb41d68bc21571a1b
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Herv'e J'egou
- Matthijs Douze
- Luc Van Gool
- Andrew Zisserman
- Cordelia Schmid
- Yi Yang
- Andrea Vedaldi
- Dacheng Tao
Citations in the corpus
- DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection (2020, result): “(2020) [57] GAN-Pipeline Features k-NN, SVM, LDA Acc.”
- The Stable Signature: Rooting Watermarks in Latent Diffusion Models (2023, background): “Detection of AI-generated/manipulated images is notably active in the context of deep-fakes [32, 107].”
- Self-Consuming Generative Models Go MAD (2023, background): “, convolutional traces [40] or aliasing artifacts [41]) that may be reinforced by self-consuming generators.”
- Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, methodology): “[159] presented an approach to detect the image manipulation.”