Source Generator Attribution via Inversion
This addresses the need for forensics in synthetic imagery, particularly for issues like deep fakes, though it is incremental as it builds on existing attribution methods for camera-captured images.
The paper tackles the problem of attributing synthetic images to specific GAN generators in a white-box setting by inverting the generation process, enabling both source identification and input recovery.
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.