Source Generator Attribution via Inversion

By Michael Albright, Scott McCloskey. 2019

57 citations recorded by the source corpus.

With advances in Generative Adversarial Networks (GANs) leading to dramatically-improved synthetic images and video, there is an increased need for algorithms which extend traditional forensics to this new category of imagery. While GANs have been shown to be helpful in a number of computer vision applications, there are other problematic uses such as `deep fakes' which necessitate such forensics. Source camera attribution algorithms using various cues have addressed this need for imagery captured by a camera, but there are fewer options for synthetic imagery. We address the problem of attributing a synthetic image to a specific generator in a white box setting, by inverting the process of generation. This enables us to simultaneously determine whether the generator produced the image and recover an input which produces a close match to the synthetic image.

Subfields: Computer Vision and Pattern Recognition

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

Citations in the corpus

Analyzing and Improving the Image Quality of StyleGAN (2019, background): “being able to attribute a fake image to its specific source [2].”
Detecting CNN-Generated Facial Images in Real-World Scenarios (2020, background): “As shown by [2, 29, 52], CNN-generated images have pixel patterns dissimilar to real images, which might become more distinctive by learning more intrinsic (pixel-level) image features, such that detection models might generalize better to unseen (e.”
Incremental learning for the detection and classification of GAN-generated images (2019, background): “Following this same path, in [13] the problem of attributing a synthetic”
GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection (2019, background): “for generating a specific image potentially synthetic [30], [31].”
Detection of AI-Generated Synthetic Faces (2022, background): “In [1, 28] attribution of GAN generated images to their source is pursued through GAN inversion.”
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation (2020, methodology): “To begin with, we compare with other GAN-inversion methods [10,2,45,5] for image reconstruction.”
Detecting and Simulating Artifacts in GAN Fake Images (2019, background): “[17] and [18] study the fingerprints of GAN models.”