# Deepfake Forensic Analysis: Source Dataset Attribution and Legal Implications of Synthetic Media Manipulation

arXiv: https://arxiv.org/abs/2505.11110 · HTML: https://mlsanity.com/paper/2505.11110/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 16 May 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [MesoNet: a Compact Facial Video Forgery Detection Network](https://mlsanity.com/paper/1809.00888/) (2018)
- [On the detection of synthetic images generated by diffusion models](https://mlsanity.com/paper/2211.00680/) (2022)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [Spatial-Phase Shallow Learning: Rethinking Face Forgery Detection in Frequency Domain](https://mlsanity.com/paper/2103.01856/) (2021)
- [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)
- [Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data](https://mlsanity.com/paper/2007.08457/) (2020)
- [Dataset Inference: Ownership Resolution in Machine Learning](https://mlsanity.com/paper/2104.10706/) (2021)
- [Noiseprint: a CNN-based camera model fingerprint](https://mlsanity.com/paper/1808.08396/) (2018)
- [In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking](https://mlsanity.com/paper/1806.02877/) (2018)
- [Image-to-Image Translation via Group-wise Deep Whitening-and-Coloring Transformation](https://mlsanity.com/paper/1812.09912/) (2018)
- [Deepfake Network Architecture Attribution](https://mlsanity.com/paper/2202.13843/) (2022)
- [DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation](https://mlsanity.com/paper/2010.00400/) (2020)
- [Exposing Lip-syncing Deepfakes from Mouth Inconsistencies](https://mlsanity.com/paper/2401.10113/) (2024)
- [GenAI Mirage: The Impostor Bias and the Deepfake Detection Challenge in the Era of Artificial Illusions](https://mlsanity.com/paper/2312.16220/) (2023)
- [Continuous fake media detection: adapting deepfake detectors to new generative techniques](https://mlsanity.com/paper/2406.08171/) (2024)
- [DeepFeatureX Net: Deep Features eXtractors based Network for discriminating synthetic from real images](https://mlsanity.com/paper/2404.15697/) (2024)
- [Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Images](https://mlsanity.com/paper/2203.09928/) (2022)

## Built on by (most cited first, 1 of 1)

- [Backdoors in Conditional Diffusion: Threats to Responsible Synthetic Data Pipelines](https://mlsanity.com/paper/2507.04726/) (2025)

## Abstract (arXiv)

Synthetic media generated by Generative Adversarial Networks (GANs) pose significant challenges in verifying authenticity and tracing dataset origins, raising critical concerns in copyright enforcement, privacy protection, and legal compliance. This paper introduces a novel forensic framework for identifying the training dataset (e.g., CelebA or FFHQ) of GAN-generated images through interpretable feature analysis. By integrating spectral transforms (Fourier/DCT), color distribution metrics, and local feature descriptors (SIFT), our pipeline extracts discriminative statistical signatures embedded in synthetic outputs. Supervised classifiers (Random Forest, SVM, XGBoost) achieve 98-99% accuracy in binary classification (real vs. synthetic) and multi-class dataset attribution across diverse GAN architectures (StyleGAN, AttGAN, GDWCT, StarGAN, and StyleGAN2). Experimental results highlight the dominance of frequency-domain features (DCT/FFT) in capturing dataset-specific artifacts, such as upsampling patterns and spectral irregularities, while color histograms reveal implicit regularization strategies in GAN training. We further examine legal and ethical implications, showing how dataset attribution can address copyright infringement, unauthorized use of personal data, and regulatory compliance under frameworks like GDPR and California's AB 602. Our framework advances accountability and governance in generative modeling, with applications in digital forensics, content moderation, and intellectual property litigation.