# Source Generator Attribution via Inversion

arXiv: https://arxiv.org/abs/1905.02259 · HTML: https://mlsanity.com/paper/1905.02259/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2019.

## Built on by (most cited first, 22 of 22)

- [Raising the Bar of AI-generated Image Detection with CLIP](https://mlsanity.com/paper/2312.00195/) (2023)
- [Towards Discovery and Attribution of Open-world GAN Generated Images](https://mlsanity.com/paper/2105.04580/) (2021)
- [Zero-Shot Detection of AI-Generated Images](https://mlsanity.com/paper/2409.15875/) (2024)
- [How to Trace Latent Generative Model Generated Images without Artificial Watermark?](https://mlsanity.com/paper/2405.13360/) (2024)
- [Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet](https://mlsanity.com/paper/2405.00196/) (2024)
- [Open Set Synthetic Image Source Attribution](https://mlsanity.com/paper/2308.11557/) (2023)
- [Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos](https://mlsanity.com/paper/2305.03713/) (2023)
- [Single-Model Attribution of Generative Models Through Final-Layer Inversion](https://mlsanity.com/paper/2306.06210/) (2023)
- [What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Network](https://mlsanity.com/paper/2307.15860/) (2023)
- [AI-Generated Faces in the Real World: A Large-Scale Case Study of Twitter Profile Images](https://mlsanity.com/paper/2404.14244/) (2024)
- [Attributable-Watermarking of Speech Generative Models](https://mlsanity.com/paper/2202.08900/) (2022)
- [How Do Deepfakes Move? Motion Magnification for Deepfake Source Detection](https://mlsanity.com/paper/2212.14033/) (2022)
- [Model Synthesis for Zero-Shot Model Attribution](https://mlsanity.com/paper/2307.15977/) (2023)
- [Identifying Adversarial Attacks on Text Classifiers](https://mlsanity.com/paper/2201.08555/) (2022)
- [Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey](https://mlsanity.com/paper/2411.17911/) (2024)
- [Training-free Source Attribution of AI-generated Images via Resynthesis](https://mlsanity.com/paper/2510.24278/) (2025)
- [IncreFA: Breaking the Static Wall of Generative Model Attribution](https://mlsanity.com/paper/2604.17736/) (2026)
- [PRADA: Probability-Ratio-Based Attribution and Detection of Autoregressive-Generated Images](https://mlsanity.com/paper/2511.20068/) (2025)
- [Deep Learning Technology for Face Forgery Detection: A Survey](https://mlsanity.com/paper/2409.14289/) (2024)
- [Fingerprints of Super Resolution Networks](https://mlsanity.com/paper/2410.21653/) (2024)
- [Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models](https://mlsanity.com/paper/2605.18132/) (2026)
- [Representation and Reference Selection in Training-Free Synthetic Image Attribution](https://mlsanity.com/paper/2607.12052/) (2026)

## Abstract (arXiv)

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.