mlsanityData to 7 Oct 2026

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

arXiv 2203.09928 ↗First posted 18 Mar 2022cs.CV cs.LG eess.IVcited by 4

Not on the map. Why?

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 34 references that are in the map. First posted on arXiv 18 Mar 2022.

Builds on

24 of 34 references.

References · 24

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  5. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  6. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  7. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  8. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  9. 2019Face X-ray for More General Face Forgery Detectioncited by 469
  10. 2019Deferred Neural Rendering: Image Synthesis using Neural Texturescited by 253
  11. 2019DRIT++: Diverse Image-to-Image Translation via Disentangled Representationscited by 244
  12. 2017AttGAN: Facial Attribute Editing by Only Changing What You Wantcited by 241
12 more
  1. 2020Media Forensics and DeepFakes: an overviewcited by 208
  2. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  3. 2020DeepFake Detection by Analyzing Convolutional Tracescited by 81
  4. 2018Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Datacited by 76
  5. 2018Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformationcited by 49
  6. 2020Adversarial Perturbations Fool Deepfake Detectorscited by 48
  7. 2021Fighting deepfakes by detecting GAN DCT anomaliescited by 39
  8. 2019On the generalization of GAN image forensicscited by 36
  9. 2020Fighting Deepfake by Exposing the Convolutional Traces on Imagescited by 24
  10. 2020Preliminary Forensics Analysis of DeepFake Imagescited by 12
  11. 2019MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translationcited by 7
  12. 2016A Classification Engine for Image Ballistics of Social Datacited by 4

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 2.

4 papers.

  1. 2023Level Up the Deepfake Detection: a Method to Effectively Discriminate Images Generated by GAN Architectures and Diffusion Modelscited by 20
  2. 2023Improving Video Deepfake Detection: A DCT-Based Approach with Patch-Level Analysiscited by 1
  3. 2025End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluationcited by 1
  4. 2025Deepfake Forensic Analysis: Source Dataset Attribution and Legal Implications of Synthetic Media Manipulationcited by 1