mlsanityData to 14 Oct 2026

Discovering Transferable Forensic Features for CNN-generated Images Detection

arXiv 2208.11342 ↗First posted 24 Aug 2022cs.CV cs.CR cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

Visual counterfeits are increasingly causing an existential conundrum in mainstream media with rapid evolution in neural image synthesis methods. Though detection of such counterfeits has been a taxing problem in the image forensics community, a recent class of forensic detectors -- universal detectors -- are able to surprisingly spot counterfeit images regardless of generator architectures, loss functions, training datasets, and resolutions. This intriguing property suggests the possible existence of transferable forensic features (T-FF) in universal detectors. In this work, we conduct the first analytical study to discover and understand T-FF in universal detectors. Our contributions are 2-fold: 1) We propose a novel forensic feature relevance statistic (FF-RS) to quantify and discover T-FF in universal detectors and, 2) Our qualitative and quantitative investigations uncover an unexpected finding: color is a critical T-FF in universal detectors. Code and models are available at https://keshik6.github.io/transferable-forensic-features/

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 68 of its 104 references that are in the map. First posted on arXiv 24 Aug 2022.

Builds on

68 of 104 references.

References · 68

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  7. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  10. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,626
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  12. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
38 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,355
  2. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  3. 2020Training Generative Adversarial Networks with Limited Datacited by 1,186
  4. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  5. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,101
  6. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,098
  7. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  8. 2014Striving for Simplicity: The All Convolutional Netcited by 990
  9. 2019CNN-generated images are surprisingly easy to spot... for nowcited by 847
  10. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  11. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
  12. 2017Wasserstein GANcited by 639
  13. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
  14. 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 504
  15. 2019Face X-ray for More General Face Forgery Detectioncited by 470
  16. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
  17. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  18. 2021Multi-attentional Deepfake Detectioncited by 341
  19. 2022Detecting Deepfakes with Self-Blended Imagescited by 338
  20. 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
  21. 2020Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detectioncited by 287
  22. 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 280
  23. 2020What makes fake images detectable? Understanding properties that generalizecited by 273
  24. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 262
  25. 2021Generalizing Face Forgery Detection with High-frequency Featurescited by 262
  26. 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 250
  27. 2016Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layerscited by 199
  28. 2019Full-Gradient Representation for Neural Network Visualizationcited by 191
  29. 2018Do GANs leave artificial fingerprints?cited by 190
  30. 2020Eigen-CAM: Class Activation Map using Principal Componentscited by 189
  31. 2020Learning Self-Consistency for Deepfake Detectioncited by 179
  32. 2018FairGAN: Fairness-aware Generative Adversarial Networkscited by 164
  33. 2017The Shattered Gradients Problem: If resnets are the answer, then what is the question?cited by 157
  34. 2020Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNscited by 151
  35. 2019Fourier Spectrum Discrepancies in Deep Network Generated Imagescited by 139
  36. 2020DeepFaceLab: Integrated, flexible and extensible face-swapping frameworkcited by 131
  37. 2019Detecting GAN generated Fake Images using Co-occurrence Matricescited by 124
  38. 2021Pathdreamer: A World Model for Indoor Navigationcited by 118

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 10; 2024: 5; 2025: 3; 2026: 4.

24 papers.

Sort:

By area:

  1. 2023Generating Images with Multimodal Language Modelscited by 260
  2. 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 164
  3. 2023Generalizable Synthetic Image Detection via Language-guided Contrastive Learningcited by 49
  4. 2023Re-thinking Model Inversion Attacks Against Deep Neural Networkscited by 39
  5. 2022Few-shot Image Generation via Adaptation-Aware Kernel Modulationcited by 33
  6. 2023Deep Image Fingerprint: Towards Low Budget Synthetic Image Detection and Model Lineage Analysiscited by 30
  7. 2025Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarioscited by 24
  8. 2024Frequency Masking for Universal Deepfake Detectioncited by 23
  9. 2023Label-Only Model Inversion Attacks via Knowledge Transfercited by 21
  10. 2024Bi-LORA: A Vision-Language Approach for Synthetic Image Detectioncited by 20
  11. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  12. 2024Which Model Generated This Image? A Model-Agnostic Approach for Origin Attributioncited by 16
12 more
  1. 2024Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yetcited by 13
  2. 2022VideoFACT: Detecting Video Forgeries Using Attention, Scene Context, and Forensic Tracescited by 9
  3. 2023On Measuring Fairness in Generative Modelscited by 8
  4. 2025CausalCLIP: Causally-Informed Feature Disentanglement and Filtering for Generalizable Detection of Generated Imagescited by 6
  5. 2024UGAD: Universal Generative AI Detector utilizing Frequency Fingerprintscited by 5
  6. 2026Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detectioncited by 3
  7. 2026ForensicConcept: Transferable Forensic Concepts for AIGI Detectioncited by 2
  8. 2023AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulationcited by 1
  9. 2023Trustworthy Large Models in Vision: A Surveycited by 0
  10. 2025Towards Sustainable Universal Deepfake Detection with Frequency-Domain Maskingcited by 0
  11. 2026Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalizationcited by 0
  12. 2026Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packagingcited by 0