# Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images

arXiv: https://arxiv.org/abs/2203.09928 · HTML: https://mlsanity.com/paper/2203.09928/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 18 Mar 2022.

## Builds on (most cited first, 24 of 24)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Face2Face: Real-time Face Capture and Reenactment of RGB Videos](https://mlsanity.com/paper/2007.14808/) (2020)
- [Face X-ray for More General Face Forgery Detection](https://mlsanity.com/paper/1912.13458/) (2019)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [DRIT++: Diverse Image-to-Image Translation via Disentangled Representations](https://mlsanity.com/paper/1905.01270/) (2019)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [Media Forensics and DeepFakes: an overview](https://mlsanity.com/paper/2001.06564/) (2020)
- [Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis](https://mlsanity.com/paper/1903.05628/) (2019)
- [DeepFake Detection by Analyzing Convolutional Traces](https://mlsanity.com/paper/2004.10448/) (2020)
- [Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data](https://mlsanity.com/paper/1802.10151/) (2018)
- [Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation](https://mlsanity.com/paper/1812.09912/) (2018)
- [Adversarial Perturbations Fool Deepfake Detectors](https://mlsanity.com/paper/2003.10596/) (2020)
- [Fighting deepfakes by detecting GAN DCT anomalies](https://mlsanity.com/paper/2101.09781/) (2021)
- [On the generalization of GAN image forensics](https://mlsanity.com/paper/1902.11153/) (2019)
- [Fighting Deepfake by Exposing the Convolutional Traces on Images](https://mlsanity.com/paper/2008.04095/) (2020)
- [Preliminary Forensics Analysis of DeepFake Images](https://mlsanity.com/paper/2004.12626/) (2020)
- [MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation](https://mlsanity.com/paper/1902.03938/) (2019)
- [A Classification Engine for Image Ballistics of Social Data](https://mlsanity.com/paper/1610.06347/) (2016)

## Built on by (most cited first, 4 of 4)

- [Level Up the Deepfake Detection: a Method to Effectively Discriminate Images Generated by GAN Architectures and Diffusion Models](https://mlsanity.com/paper/2303.00608/) (2023)
- [Improving Video Deepfake Detection: A DCT-Based Approach with Patch-Level Analysis](https://mlsanity.com/paper/2310.11204/) (2023)
- [End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation](https://mlsanity.com/paper/2504.20923/) (2025)
- [Deepfake Forensic Analysis: Source Dataset Attribution and Legal Implications of Synthetic Media Manipulation](https://mlsanity.com/paper/2505.11110/) (2025)

## Abstract (arXiv)

Most recent style-transfer techniques based on generative architectures are able to obtain synthetic multimedia contents, or commonly called deepfakes, with almost no artifacts. Researchers already demonstrated that synthetic images contain patterns that can determine not only if it is a deepfake but also the generative architecture employed to create the image data itself. These traces can be exploited to study problems that have never been addressed in the context of deepfakes. To this aim, in this paper a first approach to investigate the image ballistics on deepfake images subject to style-transfer manipulations is proposed. Specifically, this paper describes a study on detecting how many times a digital image has been processed by a generative architecture for style transfer. Moreover, in order to address and study accurately forensic ballistics on deepfake images, some mathematical properties of style-transfer operations were investigated.