GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection

By João C. Neves, Rubén Tolosana, Rubén Vera-Rodriguez, Vasco Lopes, Hugo Proencca, Julian Fierrez. 2019

165 citations recorded by the source corpus.

The availability of large-scale facial databases, together with the remarkable progresses of deep learning technologies, in particular Generative Adversarial Networks (GANs), have led to the generation of extremely realistic fake facial content, raising obvious concerns about the potential for misuse. Such concerns have fostered the research on manipulation detection methods that, contrary to humans, have already achieved astonishing results in various scenarios. In this study, we focus on the synthesis of entire facial images, which is a specific type of facial manipulation. The main contributions of this study are four-fold: i) a novel strategy to remove GAN “fingerprints” from synthetic fake images based on autoencoders is described, in order to spoof facial manipulation detection systems while keeping the visual quality of the resulting images; ii) an in-depth analysis of the recent literature in facial manipulation detection; iii) a complete experimental assessment of this type of facial manipulation, considering the state-of-the-art fake detection systems (based on holistic deep networks, steganalysis, and local artifacts), remarking how challenging is this task in unconstrained scenarios; and finally iv) we announce a novel public database, named iFakeFaceDB, yielding from the application of our proposed GAN-fingerprint Removal approach (GANprintR) to already very realistic synthetic fake images. The results obtained in our empirical evaluation show that additional efforts are required to develop robust facial manipulation detection systems against unseen conditions and spoof techniques, such as the one proposed in this study.

Subfields: Computer Vision and Pattern Recognition, Generative Models, Signal Processing

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

In Generative Models

In Signal Processing

Citations in the corpus

Detection of AI-Generated Synthetic Faces (2022, methodology): “This approach is pursued in [43], where an autoencoder-based strategy is proposed, that is trained using only real faces and is able to remove the high-frequency components that correspond to the ﬁngerprints of the models used to generate synthetic images.”
Learning Self-Consistency for Deepfake Detection (2020, background): “To detect the whole image synthesis, recent research [58, 36, 13, 52] observes that GANgenerated images contain specific cues that can be easily detected, and the trained models have exhibited good generalization ability across different synthesis methods.”
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection (2020, methodology): “This detection approach was implemented later on in [16] considering images from the 100K-Faces database, achieving an EER of 12.”
Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward (2021, methodology): “The third method uses advanced image filtering techniques to improve generation quality such as removal of fingerprints left during generation and addition of noise to remove fake signs [286-288].”