Synthetic Image Verification in the Era of Generative AI: What Works and What Isn't There Yet
Not on the map. Why?
Abstract (arXiv)
In this work we present an overview of approaches for the detection and attribution of synthetic images and highlight their strengths and weaknesses. We also point out and discuss hot topics in this field and outline promising directions for future research.
Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 67 of its 84 references that are in the map. First posted on arXiv 30 Apr 2024.
Builds on
67 of 84 references.
References · 67
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
- 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2022Scalable Diffusion Models with Transformerscited by 5,931
- 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
- 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
38 more
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
- 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
- 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
- 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
- 2021Alias-Free Generative Adversarial Networkscited by 1,181
- 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
- 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
- 2019CNN-generated images are surprisingly easy to spot... for nowcited by 842
- 2020Leveraging Frequency Analysis for Deep Fake Image Recognitioncited by 501
- 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
- 2023Towards Universal Fake Image Detectors that Generalize Across Generative Modelscited by 483
- 2023DIRE for Diffusion-Generated Image Detectioncited by 386
- 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
- 2023GenImage: A Million-Scale Benchmark for Detecting AI-Generated Imagecited by 318
- 2019Detecting and Simulating Artifacts in GAN Fake Imagescited by 293
- 2022On the detection of synthetic images generated by diffusion modelscited by 282
- 2020Watch your Up-Convolution: CNN Based Generative Deep Neural Networks are Failing to Reproduce Spectral Distributionscited by 278
- 2020What makes fake images detectable? Understanding properties that generalizecited by 272
- 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
- 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
- 2018Do GANs leave artificial fingerprints?cited by 188
- 2023Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detectioncited by 180
- 2022DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Modelscited by 167
- 2023Raising the Bar of AI-generated Image Detection with CLIPcited by 163
- 2021Are GAN generated images easy to detect? A critical analysis of the state-of-the-artcited by 139
- 2023Intriguing properties of synthetic images: from generative adversarial networks to diffusion modelscited by 121
- 2022Towards the Detection of Diffusion Model Deepfakescited by 111
- 2018ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detectioncited by 104
- 2023Identifying and Mitigating the Security Risks of Generative AIcited by 90
- 2022Fusing Global and Local Features for Generalized AI-Synthesized Image Detectioncited by 88
- 2023GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesiscited by 84
- 2023CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Imagescited by 84
- 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
- 2023Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for nowcited by 61
- 2019Incremental learning for the detection and classification of GAN-generated imagescited by 58
- 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
50 most cited of 67 All 67 (JSON)
Built on by
Citing papers per year: 2024: 6; 2025: 4; 2026: 3.
13 papers.
Sort:
By area:
- 2024A Bias-Free Training Paradigm for More General AI-generated Image Detectioncited by 67
- 2024Any-Resolution AI-Generated Image Detection by Spectral Learningcited by 56
- 2024TGIF: Text-Guided Inpainting Forgery Datasetcited by 20
- 2024Exploring the Adversarial Robustness of CLIP for AI-generated Image Detectioncited by 11
- 2025AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detectioncited by 10
- 2025Generalized Design Choices for Deepfake Detectorscited by 2
- 2026Quality-Aware Calibration for AI-Generated Image Detection in the Wildcited by 2
- 2024The Tug-of-War Between Deepfake Generation and Detectioncited by 1
- 2026Synthetic Image Detection with CLIP: Understanding and Assessing Predictive Cuescited by 1
- 2024Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usagecited by 0
- 2025Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detectioncited by 0
- 2025Don't Guess, Escalate: Towards Explainable Uncertainty-Calibrated AI Forensic Agentscited by 0
1 more
- 2026Understanding Why Foundation Models Work for Diffusion-Generated Image Detection12 Aug 2026
- 2026Quality-Aware Calibration for AI-Generated Image Detection in the Wild16 Apr 2026
- 2026Synthetic Image Detection with CLIP: Understanding and Assessing Predictive Cues12 Feb 2026
- 2025Don't Guess, Escalate: Towards Explainable Uncertainty-Calibrated AI Forensic Agents18 Dec 2025
- 2025Generalized Design Choices for Deepfake Detectors26 Nov 2025
- 2025Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection3 Jun 2025
- 2025AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection29 Apr 2025
- 2024A Bias-Free Training Paradigm for More General AI-generated Image Detection23 Dec 2024
- 2024Any-Resolution AI-Generated Image Detection by Spectral Learning28 Nov 2024
- 2024Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage22 Nov 2024
- 2024Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection28 Jul 2024
- 2024TGIF: Text-Guided Inpainting Forgery Dataset16 Jul 2024
1 more
- 2024The Tug-of-War Between Deepfake Generation and Detection8 Jul 2024
- 2024A Bias-Free Training Paradigm for More General AI-generated Image Detectioncited by 67
- 2024Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usagecited by 0
- 2026Understanding Why Foundation Models Work for Diffusion-Generated Image Detectioncited by 0
- 2026Understanding Why Foundation Models Work for Diffusion-Generated Image Detection12 Aug 2026
- 2024A Bias-Free Training Paradigm for More General AI-generated Image Detection23 Dec 2024
- 2024Exploiting Watermark-Based Defense Mechanisms in Text-to-Image Diffusion Models for Unauthorized Data Usage22 Nov 2024
- 2024Any-Resolution AI-Generated Image Detection by Spectral Learningcited by 56
- 2024TGIF: Text-Guided Inpainting Forgery Datasetcited by 20
- 2024Exploring the Adversarial Robustness of CLIP for AI-generated Image Detectioncited by 11
- 2025AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detectioncited by 10
- 2025Generalized Design Choices for Deepfake Detectorscited by 2
- 2026Quality-Aware Calibration for AI-Generated Image Detection in the Wildcited by 2
- 2024The Tug-of-War Between Deepfake Generation and Detectioncited by 1
- 2026Synthetic Image Detection with CLIP: Understanding and Assessing Predictive Cuescited by 1
- 2025Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detectioncited by 0
- 2025Don't Guess, Escalate: Towards Explainable Uncertainty-Calibrated AI Forensic Agentscited by 0
- 2026Quality-Aware Calibration for AI-Generated Image Detection in the Wild16 Apr 2026
- 2026Synthetic Image Detection with CLIP: Understanding and Assessing Predictive Cues12 Feb 2026
- 2025Don't Guess, Escalate: Towards Explainable Uncertainty-Calibrated AI Forensic Agents18 Dec 2025
- 2025Generalized Design Choices for Deepfake Detectors26 Nov 2025
- 2025Enhancing Abnormality Identification: Robust Out-of-Distribution Strategies for Deepfake Detection3 Jun 2025
- 2025AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection29 Apr 2025
- 2024Any-Resolution AI-Generated Image Detection by Spectral Learning28 Nov 2024
- 2024Exploring the Adversarial Robustness of CLIP for AI-generated Image Detection28 Jul 2024
- 2024TGIF: Text-Guided Inpainting Forgery Dataset16 Jul 2024
- 2024The Tug-of-War Between Deepfake Generation and Detection8 Jul 2024