mlsanityData to 7 Oct 2026

Detecting GAN-generated Images by Orthogonal Training of Multiple CNNs

arXiv 2203.02246 ↗First posted 4 Mar 2022cs.CV cs.AIcited by 46

Not on the map. Why?

Abstract (arXiv)

In the last few years, we have witnessed the rise of a series of deep learning methods to generate synthetic images that look extremely realistic. These techniques prove useful in the movie industry and for artistic purposes. However, they also prove dangerous if used to spread fake news or to generate fake online accounts. For this reason, detecting if an image is an actual photograph or has been synthetically generated is becoming an urgent necessity. This paper proposes a detector of synthetic images based on an ensemble of Convolutional Neural Networks (CNNs). We consider the problem of detecting images generated with techniques not available at training time. This is a common scenario, given that new image generators are published more and more frequently. To solve this issue, we leverage two main ideas: (i) CNNs should provide orthogonal results to better contribute to the ensemble; (ii) original images are better defined than synthetic ones, thus they should be better trusted at testing time. Experiments show that pursuing these two ideas improves the detector accuracy on NVIDIA's newly generated StyleGAN3 images, never used in training.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Builds on 19 of its 25 references that are in the map. First posted on arXiv 4 Mar 2022.

Builds on

19 of 25 references.

References · 19

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  7. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  8. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  9. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
  10. 2018Albumentations: fast and flexible image augmentationscited by 558
  11. 2020One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencingcited by 438
  12. 2018Do GANs leave artificial fingerprints?cited by 188
7 more
  1. 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
  2. 2020Video Face Manipulation Detection Through Ensemble of CNNscited by 63
  3. 2020CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysiscited by 42
  4. 2021Towards Universal GAN Image Detectioncited by 26
  5. 2021More Real than Real: A Study on Human Visual Perception of Synthetic Facescited by 23
  6. 2020Training CNNs in Presence of JPEG Compression: Multimedia Forensics vs Computer Visioncited by 17
  7. 2021Forensic Analysis of Synthetically Generated Western Blot Imagescited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 6; 2024: 13; 2025: 17; 2026: 7.

46 papers.

Sort:

By area:

  1. 2023DIRE for Diffusion-Generated Image Detectioncited by 386
  2. 2022On the detection of synthetic images generated by diffusion modelscited by 282
  3. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
  4. 2022Towards the Detection of Diffusion Model Deepfakescited by 111
  5. 2024Zero-Shot Detection of AI-Generated Imagescited by 50
  6. 2024On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detectioncited by 40
  7. 2023Parents and Children: Distinguishing Multimodal DeepFakes from Natural Imagescited by 29
  8. 2022GLFF: Global and Local Feature Fusion for AI-synthesized Image Detectioncited by 25
  9. 2025Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarioscited by 24
  10. 2023Improving Synthetically Generated Image Detection in Cross-Concept Settingscited by 15
  11. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  12. 2024Which Model Generated This Image? A Model-Agnostic Approach for Origin Attributioncited by 15
34 more
  1. 2024Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yetcited by 13
  2. 2025Methods and Trends in Detecting AI-Generated Images: A Comprehensive Reviewcited by 12
  3. 2024Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detectioncited by 10
  4. 2025Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detectioncited by 10
  5. 2024Towards the Detection of AI-Synthesized Human Face Imagescited by 8
  6. 2025Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?cited by 8
  7. 2024When Synthetic Traces Hide Real Content: Analysis of Stable Diffusion Image Launderingcited by 7
  8. 2024Deepfake Media Forensics: State of the Art and Challenges Aheadcited by 6
  9. 2023Synthetic Image Detection: Highlights from the IEEE Video and Image Processing Cup 2022 Student Competitioncited by 5
  10. 2024Artifact Feature Purification for Cross-domain Detection of AI-generated Imagescited by 5
  11. 2025Detecting Generated Images by Fitting Natural Image Distributionscited by 5
  12. 2025RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectorscited by 4
  13. 2025ForenX: Towards Explainable AI-Generated Image Detection with Multimodal Large Language Modelscited by 4
  14. 2024Epistemic Uncertainty for Generated Image Detectioncited by 3
  15. 2025Can GPT tell us why these images are synthesized? Empowering Multimodal Large Language Models for Forensicscited by 3
  16. 2024Landscape More Secure Than Portrait? Zooming Into the Directionality of Digital Images With Security Implicationscited by 2
  17. 2024Localization of Synthetic Manipulations in Western Blot Imagescited by 2
  18. 2025Generalized Design Choices for Deepfake Detectorscited by 2
  19. 2025Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detectioncited by 2
  20. 2024The Visual Counter Turing Test (VCT2): A Benchmark for Evaluating AI-Generated Image Detection and the Visual AI Index (VAI)cited by 1
  21. 2025Knowledge-Guided Prompt Learning for Deepfake Facial Image Detectioncited by 1
  22. 2025Provenance Detection for AI-Generated Images: Combining Perceptual Hashing, Homomorphic Encryption, and AI Detection Modelscited by 1
  23. 2025Exploring the Collaborative Advantage of Low-level Information on Generalizable AI-Generated Image Detectioncited by 1
  24. 2025Where's the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Contentcited by 1
  25. 2025LDR-Net: A Novel Framework for AI-generated Image Detection via Localized Discrepancy Representationcited by 0
  26. 2025A Novel Local Focusing Mechanism for Deepfake Detection Generalizationcited by 0
  27. 2025Consolidating Diffusion-Generated Video Detection with Unified Multimodal Forgery Learningcited by 0
  28. 2026Degradation-Consistent Paired Training for Robust AI-Generated Image Detectioncited by 0
  29. 2026Boosting Robust AIGI Detection with LoRA-based Pairwise Trainingcited by 0
  30. 2026CHROMA: Detecting AI-Generated Images through Inter-Channel Color-Space Correlationscited by 0
  31. 2026Minimalist Preprocessing Approach for Image Synthesis Detectioncited by 0
  32. 2026Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detectioncited by 0
  33. 2026Training-Free Reconstruction-Based AI-Generated Image Detectors Are Inherently Vulnerable to Adversarial Examplescited by 0
  34. 2026Trustworthy synthetic visual media: Evidence across the media lifecyclecited by 0