mlsanityData to 14 Oct 2026

DeepFake Detection by Analyzing Convolutional Traces

arXiv 2004.10448 ↗First posted 22 Apr 2020cs.CVcited by 81

Not on the map. Why?

Abstract (arXiv)

The Deepfake phenomenon has become very popular nowadays thanks to the possibility to create incredibly realistic images using deep learning tools, based mainly on ad-hoc Generative Adversarial Networks (GAN). In this work we focus on the analysis of Deepfakes of human faces with the objective of creating a new detection method able to detect a forensics trace hidden in images: a sort of fingerprint left in the image generation process. The proposed technique, by means of an Expectation Maximization (EM) algorithm, extracts a set of local features specifically addressed to model the underlying convolutional generative process. Ad-hoc validation has been employed through experimental tests with naive classifiers on five different architectures (GDWCT, STARGAN, ATTGAN, STYLEGAN, STYLEGAN2) against the CELEBA dataset as ground-truth for non-fakes. Results demonstrated the effectiveness of the technique in distinguishing the different architectures and the corresponding generation process.

Key facts. Cited by 81 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 13; 2023: 21; 2024: 13; 2025: 10; 2026: 8.

81 papers.

Sort:

By area:

  1. 2023DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvaturecited by 726
  2. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 304
  3. 2023Self-Consuming Generative Models Go MADcited by 250
  4. 2021ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysiscited by 126
  5. 2024Best Practices and Lessons Learned on Synthetic Datacited by 106
  6. 2023Identifying and Mitigating the Security Risks of Generative AIcited by 91
  7. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  8. 2021Combining EfficientNet and Vision Transformers for Video Deepfake Detectioncited by 82
  9. 2022FrePGAN: Robust Deepfake Detection Using Frequency-level Perturbationscited by 75
  10. 2023Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesiscited by 72
  11. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  12. 2021Countering Malicious DeepFakes: Survey, Battleground, and Horizoncited by 56
38 more
  1. 2022Deepfake Detection: A Comprehensive Survey from the Reliability Perspectivecited by 50
  2. 2023Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localizationcited by 43
  3. 2021Fighting deepfakes by detecting GAN DCT anomaliescited by 39
  4. 2024Faster Than Lies: Real-time Deepfake Detection using Binary Neural Networkscited by 27
  5. 2021Deepfake Detection Scheme Based on Vision Transformer and Distillationcited by 22
  6. 2024ManiFPT: Defining and Analyzing Fingerprints of Generative Modelscited by 18
  7. 2022Model Attribution of Face-swap Deepfake Videoscited by 17
  8. 2023VIVE3D: Viewpoint-Independent Video Editing using 3D-Aware GANscited by 16
  9. 2022On the Exploitation of Deepfake Model Recognitioncited by 14
  10. 2023Securing Deep Generative Models with Universal Adversarial Signaturecited by 14
  11. 2022Analyzing Fairness in Deepfake Detection With Massively Annotated Databasescited by 13
  12. 2022D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensemblescited by 11
  13. 2023EKILA: Synthetic Media Provenance and Attribution for Generative Artcited by 11
  14. 2021Multi-Modal Semantic Inconsistency Detection in Social Media News Postscited by 10
  15. 2023GenAI Mirage: The Impostor Bias and the Deepfake Detection Challenge in the Era of Artificial Illusionscited by 10
  16. 2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
  17. 2021Geo-DefakeHop: High-Performance Geographic Fake Image Detectioncited by 9
  18. 2024XAI-Based Detection of Adversarial Attacks on Deepfake Detectorscited by 9
  19. 2025SyncTalk++: High-Fidelity and Efficient Synchronized Talking Heads Synthesis Using Gaussian Splattingcited by 9
  20. 2024FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Spacecited by 8
  21. 2025Riemannian-Geometric Fingerprints of Generative Modelscited by 8
  22. 2024Deepfake Media Forensics: State of the Art and Challenges Aheadcited by 7
  23. 2021DeepFake Detection with Inconsistent Head Poses: Reproducibility and Analysiscited by 6
  24. 2023VADER: Video Alignment Differencing and Retrievalcited by 6
  25. 2022How Do Deepfakes Move? Motion Magnification for Deepfake Source Detectioncited by 5
  26. 2023RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detectioncited by 5
  27. 2021MD-CSDNetwork: Multi-Domain Cross Stitched Network for Deepfake Detectioncited by 4
  28. 2022Deepfake Style Transfer Mixture: a First Forensic Ballistics Study on Synthetic Imagescited by 4
  29. 2021What's wrong with this video? Comparing Explainers for Deepfake Detectioncited by 3
  30. 2021Improved Xception with Dual Attention Mechanism and Feature Fusion for Face Forgery Detectioncited by 3
  31. 2023Deepfake Detection Analyzing Hybrid Dataset Utilizing CNN and SVMcited by 3
  32. 2023CapST: Leveraging Capsule Networks and Temporal Attention for Accurate Model Attribution in Deep-fake Videoscited by 3
  33. 2024Generalized Deepfake Attributioncited by 3
  34. 2025FakeParts: a New Family of AI-Generated DeepFakescited by 3
  35. 2022Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detectioncited by 2
  36. 2024WWW: Where, Which and Whatever Enhancing Interpretability in Multimodal Deepfake Detectioncited by 2
  37. 2025FAME: A Lightweight Spatio-Temporal Network for Model Attribution of Face-Swap Deepfakescited by 2
  38. 2025Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprintscited by 2

50 most cited of 81 All 81 (JSON)