# Generalized Deepfake Attribution

arXiv: https://arxiv.org/abs/2406.18278 · HTML: https://mlsanity.com/paper/2406.18278/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 30 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Builds on (most cited first, 21 of 21)

- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Leveraging Frequency Analysis for Deep Fake Image Recognition](https://mlsanity.com/paper/2003.08685/) (2020)
- [Multi-attentional Deepfake Detection](https://mlsanity.com/paper/2103.02406/) (2021)
- [Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributions](https://mlsanity.com/paper/2003.01826/) (2020)
- [What makes fake images detectable? Understanding properties that generalize](https://mlsanity.com/paper/2008.10588/) (2020)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data](https://mlsanity.com/paper/2007.08457/) (2020)
- [Do GANs leave artificial fingerprints?](https://mlsanity.com/paper/1812.11842/) (2018)
- [Responsible Disclosure of Generative Models Using Scalable Fingerprinting](https://mlsanity.com/paper/2012.08726/) (2020)
- [DeepFake Detection by Analyzing Convolutional Traces](https://mlsanity.com/paper/2004.10448/) (2020)
- [Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images](https://mlsanity.com/paper/2106.07873/) (2021)
- [Deepfake Network Architecture Attribution](https://mlsanity.com/paper/2202.13843/) (2022)
- [T-GD: Transferable GAN-generated Images Detection Framework](https://mlsanity.com/paper/2008.04115/) (2020)
- [DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning](https://mlsanity.com/paper/2104.11507/) (2021)
- [Decentralized Attribution of Generative Models](https://mlsanity.com/paper/2010.13974/) (2020)
- [Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning](https://mlsanity.com/paper/1912.11082/) (2019)

## Built on by (most cited first, 3 of 3)

- [Modelship Attribution: Tracing Multi-Stage Manipulations Across Generative Models](https://mlsanity.com/paper/2506.02405/) (2025)
- [Exploiting the Final Component of Generator Architectures for AI-Generated Image Detection](https://mlsanity.com/paper/2601.20461/) (2026)
- [Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection](https://mlsanity.com/paper/2409.08884/) (2024)

## Abstract (arXiv)

The landscape of fake media creation changed with the introduction of Generative Adversarial Networks (GAN s). Fake media creation has been on the rise with the rapid advances in generation technology, leading to new challenges in Detecting fake media. A fundamental characteristic of GAN s is their sensitivity to parameter initialization, known as seeds. Each distinct seed utilized during training leads to the creation of unique model instances, resulting in divergent image outputs despite employing the same architecture. This means that even if we have one GAN architecture, it can produce countless variations of GAN models depending on the seed used. Existing methods for attributing deepfakes work well only if they have seen the specific GAN model during training. If the GAN architectures are retrained with a different seed, these methods struggle to attribute the fakes. This seed dependency issue made it difficult to attribute deepfakes with existing methods. We proposed a generalized deepfake attribution network (GDA-N et) to attribute fake images to their respective GAN architectures, even if they are generated from a retrained version of the GAN architecture with a different seed (cross-seed) or from the fine-tuned version of the existing GAN model. Extensive experiments on cross-seed and fine-tuned data of GAN models show that our method is highly effective compared to existing methods. We have provided the source code to validate our results.