Awesome AI-generated Image Detection

A collection list of AI-generated image detection related datasets, tools, papers, and code.

If you want to contribute to this list, welcome to send me a pull request or contact me :)

• :globe_with_meridians: Project Page
• :octocat: Code
• :bricks: Datasets Download Link

TODOs

• Add NeurIPS 2025 papers
• Add ICCV 2025 papers

---

Use the Table of Contents to quickly browse the repository and jump to the sections you need. It provides direct links to each conference and year, so you can navigate the content without scrolling.

• Benchmark / Survey
• Datasets
• 🔥 Arxiv
• CVPR
  • 🔥 CVPR 2025
  • CVPR 2024
  • CVPR 2023
  • CVPR 2020
• ICCV
  • 🔥 ICCV 2025
  • ICCV 2023
• ICML
  • 🔥 ICML 2025
  • ICML 2024
  • ICML 2020
• NeurIPS
  • 🔥 NeurIPS 2025
  • NeurIPS 2024
• ICLR
  • 🔥 ICLR 2026 *PrePrint*
  • ICLR 2025
• AAAI
  • AAAI 2025
  • AAAI 2024
• MM
  • MM 2025
• KDD
  • KDD 2025
• ECCV
  • ECCV 2024
  • ECCV 2022
  • ECCV 2020
• ICMR
  • ICMR 2024
• CCS
  • CCS 2024
• ICIP
  • ICIP 2022
• WIFS
  • WIFS 2019
• ICASSP
  • ICASSP
• Others
  • Tools

Benchmark/Survey

• Is Artificial Intelligence Generated Image Detection a Solved Problem? (Ziqiang Li et al., NeurIPS 2025) :octocat: :bricks:

• AI-GenBench: A New Ongoing Benchmark for AI-Generated Image Detection (Lorenzo Pellegrini et al., IJCNN workshop 2025) :octocat:

• Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images (Zuyu Lu et al., NeurIPS 2023) :octocat:

• Recent Advances on Generalizable Diffusion-generated Image Detection (Qijie Xu et al., arxiv 2025) :octocat:

Back to TOC ↑

Datasets

• Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation (Siwei Wen et al., NeurIPS 2025) :octocat: :bricks:

• CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI (Siyuan Cheng et al., CVPR2025) :octocat: :bricks:

• LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models (Junyan Ye et al., ICLR 2025 spotlight) :octocat: :globe_with_meridians: :bricks:

• AIDE: A Sanity Check for AI-generated Image Detection (Shilin Yan et al., ICLR 2025) :octocat: :bricks:

• ImagiNet: A Multi-Content Dataset for Generalizable Synthetic Image Detection via Contrastive Learning (Delyan Boychev et al., ECCV 2024) :octocat: :bricks:

• DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of Diffusion Generated Images (Baoying Chen et al., ICML 2024) :octocat: :bricks:

• Synthbuster: Towards detection of diffusion model generated images. :bricks:

• GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image (Mingjian Zhu et al., NeurIPS 2023) :globe_with_meridians: :octocat: :bricks:

• CNNDetect: CNN-generated images are surprisingly easy to spot...for now (Sheng-Yu Wang et al., CVPR 2020) :globe_with_meridians: :octocat: :bricks:

Back to TOC ↑

NeurIPS 2025

• Towards Generalizable Detector for Generated Image (Qianshu Cai et al., NeurIPS 2025) :octocat:

• ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization (Bo Du et al., NeurIPS 2025) :octocat: :globe_with_meridians:

• Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation (Siwei Wen et al., NeurIPS 2025) :octocat: :bricks:

• FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies (Shuqao Liang et al., NeurIPS 2025)

• Is Artificial Intelligence Generated Image Detection a Solved Problem? (Ziqiang Li et al., NeurIPS 2025) :octocat: :bricks:

• Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable (Ruoxin Chen et al., NeurIPS 2025 Spotlight) :octocat:

• MLEP: Multi-granularity Local Entropy Patterns for Generalized AI-generated Image Detection (Lin Yuan et al., NeurIPS 2025)

• [Training-free Detection of AI-generated images via Cropping Robustness] (Sungik Choi et al., NeurIPS 2025)

• [Denoising Trajectory Analysis for Zero-Shot AI-Generated Image Detection] (Yachao Liang et al., NeurIPS 2025)

Back to TOC ↑

ICCV 2025

• CatAID: Category-Guided AI-Generated Image Detection via Vision-Language Model Adaptation (Yu Cai et al., ICCV Workshop 2025)

• LEGION: Learning to Ground and Explain for Synthetic Image Detection (Hengrui Kang et al., ICCV 2025) :octocat:

• ForgeLens: Data-Efficient Forgery Focus for Generalizable Forgery Image Detection (Yingjian Chen et al., ICCV 2025)

• AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models (Ziyin Zhou et al., ICCV 2025) :octocat:

• D3QE: Learning Discrete Distribution Discrepancy-aware Quantization Error for Autoregressive-Generated Image Detection (Yanran Zhang et al., ICCV 2025) :octocat:

• LOTA: Bit-Planes Guided AI-Generated Image Detection (Renxi Cheng et al., ICCV 2025)

• Forensic-MoE: Exploring Comprehensive Synthetic Image Detection Traces with Mixture of Experts (Mingqi Fang et al., ICCV 2025) :octocat:

• Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios (Chunxiao Li et al., ICCV 2025)

• Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detection (Yingsong Huang et al., ICCV 2025)

Back to TOC ↑

ICML 2025

• Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection (Zhiyuan Yan et al., ICML 2025 Oral) :octocat:

• Stay-Positive: A Case for Ignoring Real Image Features in Fake Image Detection (Anirudh Sundara Rajan et al., ICML 2025) :octocat: :globe_with_meridians:

• Are High-Quality AI-Generated Images More Difficult for Models to Detect? (Yao Xiao et al., ICML 2025)

• Few-Shot Learner Generalizes Across AI-Generated Image Detection (Shiyu Wu et al., ICML 2025) :octocat:

• PiD: Generalized AI-Generated Images Detection with Pixelwise Decomposition Residuals (Xinghe Fu et al., ICML 2025)

Back to TOC ↑

CVPR 2025

• Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images (Tai Nguyen et al., CVPR 2025)

• Beyond Generation: A Diffusion-based Low-level Feature Extractor for Detecting AI-generated Images (Nan Zhong et al., CVPR 2025)

• Towards Universal AI-Generated Image Detection by Variational Information Bottleneck Network (Haifeng Zhang et al., CVPR 2025) :octocat:

• A Bias-Free Training Paradigm for More General AI-generated Image Detection (Fabrizio Guilaro et al., CVPR 2025)

• Secret Lies in Color: Enhancing AI-Generated Images Detection with Color Distribution Analysis (Zexi Jia et al., CVPR 2025)

• FIRE: Robust Detection of Diffusion-Generated Images via Frequency-Guided Reconstruction Error (Beilin Chu et al., CVPR 2025) :octocat:

• Community Forensics: Using Thousands of Generators to Train Fake Image Detectors (Jeongsoo Park et al., CVPR 2025) :global_with_meridians: :octocat:

• Any-Resolution AI-Generated Image Detection by Spectral Learning (Dimitrios Karageorgiou et al., CVPR 2025) :octocat:

• CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI (Siyuan Cheng et al., CVPR2025) :octocat:

Back to TOC ↑

ICLR 2025

• A Sanity Check for AI-generated Image Detection (Shilin Yan et al., ICLR 2025) :octocat:

• Aligned Datasets Improve Detection of Latent Diffusion-Generated Images (Anirudh Sundara Rajan et al., ICLR 2025) :globe_with_meridians: :octocat:

• Manifold Induced Biases for Zero-shot and Few-shot Detection of Generated Images (Jonathan Brokman et al., ICLR 2025)

• LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models (Junyan Ye et al., ICLR 2025 spotlight) :octocat: :globe_with_meridians: :bricks:

Back to TOC ↑

AAAI 2025

• C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection (Chuangchuang Tan et al., AAAI 2025) :octocat:

Back to TOC ↑

MM 2025

• Towards Good Generalizations for Diffusion Generated Image Detection Using Multiple Reconstruction Contrastive Learning (Wanyi Zhuang et al., MM 2025)

Back to TOC ↑

KDD 2025

• Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective (Ouxiang Li, KDD 2025) :octocat:

Back to TOC ↑

CVPR 2024

• FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion (George Cazenavette et al., CVPR 2024) :globe_with_meridians:

• Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection (Huan Liu et al., CVPR 2024) :octocat:

• LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection (Yunpeng Luo et al., CVPR 2024) :octocat:

• AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error (Jonas Ricker et al., CVPR 2024) :octocat:

• Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection (Chuangchuang Tan et al., CVPR 2024) :octocat:

• Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now (Ayush Sarkar et al., CVPR24) :globe_with_meridians: :octocat:

Back to TOC ↑

ICML 2024

• DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of Diffusion Generated Images (Baoying Chen et al., ICML 2024) :octocat:

Back to TOC ↑

ECCV 2024

• Zero-Shot Detection of AI-Generated Images (Davide Cozzolino et al., ECCV 2024):globe_with_meridians: :octocat:

• Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection (Christos Koutlis et al., ECCV 2024) :octocat:

• Your diffusion model is an implicit synthetic image detector (Xi Wang et al, ECCV Workshop 2024)

Back to TOC ↑

ICMR 2024

• Clipping the deception: Adapting vision-language models for universal deepfake detection (Sohail Ahmed Khan et al., ICMR 2024) :octocat:

Back to TOC ↑

CCS 2024

• De-fake: Detection and attribution of fake images generated by text-to-image generation models (Zeyang Sha et al., CCS 2024) :octocat:

Back to TOC ↑

AAAI 2024

• Frequency-aware deepfake detection: Improving generalizability through frequency space domain learning (Chuangchuang Tan et al., AAAI 2024) :octocat:

Back to TOC ↑

NeurIPS 2024

• Breaking Semantic Artifacts for Generalized AI-generated Image Detection (Chende Zhang et al., NeurIPS 2024) :octocat:

Back to TOC ↑

CVPR 2023

• Learning on gradients: Generalized artifacts representation for gan-generated images detection (Chuangchuang Tan et al., CVPR 2023) :octocat:

• Towards Universal Fake Image Detectors that Generalize Across Generative Models (Utkarsh Ojha et al., CVPR 2023) :octocat:

Back to TOC ↑

ICCV 2023

• DIRE for Diffusion-Generated Image Detection (Zhendong Wang et al., ICCV 2023) :octocat:

Back to TOC ↑

ICIP 2022

• Fusing global and local features for generalized ai-synthesized image detection (Yan Ju et al., ICIP 2022) :octocat:

Back to TOC ↑

ECCV 2022

• Detecting generated images by real images (Bo Liu et al., ECCV 2022) :octocat:

Back to TOC ↑

CVPR 2020

• Global Texture Enhancement for Fake Face Detection in the Wild (Zhengzhe Liu et al., CVPR 2020) :octocat:

• CNNDetect: CNN-generated images are surprisingly easy to spot...for now (Sheng-Yu Wang et al., CVPR 2020) :globe_with_meridians: :octocat:

Back to TOC ↑

ECCV 2020

• What makes fake images detectable? Understanding properties that generalize (Lucy Chai et al., ECCV 2020) :globe_with_meridians: :octocat:

Back to TOC ↑

ICML 2020

• Leveraging frequency analysis for deep fake image recognition (Joel Frank et al., ICML 2020) :octocat:

Back to TOC ↑

WIFS 2019

• Detecting and simulating artifacts in gan fake images (Xu Zhang et al., WIFS 2019) :octocat:

Back to TOC ↑

ICASSP

• ReTD: Reconstruction-Based Traceability Detection for Generated Images (Weizhou Chen et al., ICASSP 2025) :octocat:

• Spatial-Temporal Reconstruction Error for AIGC-based Forgery Image Detection (Chengji Shen et al., ICASSP 2025)

• Frequency Masking for Universal DeepFake Detection (Chandler Timm Doloriel et al., ICASSP 2024) :octocat:

• On the detection of synthetic images generated by diffusion models (Riccardo Corvi et al., ICASSP 2023) :globe_with_meridians: :octocat:

Back to TOC ↑

ICLR 2026 preprint

• So-Fake: Benchmarking Social Media Image Forgery Detection

• LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detection

• Taming the Forensic Singularity: A Regularized Hyperbolic Framework for Generalizable AI-Generated Image Detection

• Redefining Generalization in Visual Domains: A Two-Axis Framework for Fake Image Detection with FusionDetect

• Training-free AI-generated Image Detection via Spectral Artifacts

• RAID: Towards Robust AI-Generated Image Detection with Bit Reversed Images

• Generalization through Discrepancy: Leveraging Distributional Fitting Gaps for AI-Generated Image Detection

• No Pixel Left Behind: A Detail-Preserving Architecture for Robust High-Resolution AI-Generated Image Detection

• All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning

• FakeXplain: AI-Generated Images Detection via Human-Aligned Grounded Reasoning

• Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection

• Semantic Visual Anomaly Detection and Reasoning in AI-Generated Images

• Triggering Generative Collapse: A Contrastive Inversion Framework for AI-Generated Image Detection

• Intermediate Representations are Strong Training-Free AI-Generated Image Detectors

• AIGID-RFT: Reinforcement Fine-Tuning Multimodal LLMs for AI-Generated Image Detection

• Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection

• SARE: Semantic-Aware Reconstruction Error for Generalizable AI-Generated Image Detection

• OmniDFA: A Unified Framework for Open Set Synthesis Image Detection and Few-Shot Attribution

• Zoom-In to Sort AI-Generated Images Out

• DiffSeg30k: A Multi-Turn Diffusion Editing Benchmark for Localized AIGC Detection

• NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localization

• Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection

• A Rich Knowledge Space for Scalable Deepfake Detection

• DeFake: Data-Efficient Adaptation for Generalized Deepfake Detection

• Adaptive Gray: Reducing Color Dependency to Improve Generalization in Deepfake Detection

• Synthetic Image Detection via Curvature of Diffusion Probability Flows

• Scaling Laws for Deepfake Detection

• HSIC Bottleneck for Cross-Generator and Domain-Incremental Synthetic Image Detection

Back to TOC ↑

Arxiv

2025

• Brought a Gun to a Knife Fight: Modern VFM Baselines Outgun Specialized Detectors on In-the-Wild AI Image Detection (Yue Zhou et al., arxiv 2025)

• TrueMoE: Dual-Routing Mixture of Discriminative Experts for Synthetic Image Detection (Laixin Zhang et al., arxiv 2025)

• All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning (Zheng Yang et al., arxiv 2025)

• Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation (Siwei Wen et al., arxiv 2025) :octocat:

• Explainable Synthetic Image Detection through Diffusion Timestep Ensembling (Yixin Wu et al., arxiv 2025)

• SFLD: Reducing the content bias for AI-generated Image Detection (Seoyeon Gye et al., arxiv 2025)

2024

• A Single Simple Patch is All You Need for AI-generated Image Detection (Jiaxuan Chen et al., arxiv 2024) :octocat:

• HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images (Sungik Choi et al, arxiv 2024)

• Learning on Less: Constraining Pre-trained Model Learning for Generalizable Diffusion-Generated Image Detection (Yingjian Chen et al, arxiv 2024)

• Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models (Chengdong Dong et al., arxiv 2024)

• Time Step Generating: A Universal Synthesized Deepfake Image Detector (Ziyue Zeng et al., arxiv 2024) :octocat:

• RIGID: A Training-Free and Model-Agnostic Framework for Robust AI-Generated Image Detection (Davide Cozzolino et al., arxiv 2024)

• FakeBench: Probing Explainable Fake Image Detection via Large Multimodal Models (Yixuan Li at al., arxiv 2024)

• Mixture of Low-rank Experts for Transferable AI-Generated Image Detection (Zihan Liu et al., arxiv 2024) :octocat:

• Guided and Fused: Efficient Frozen CLIP-ViT with Feature Guidance and Multi-Stage Feature Fusion for Generalizable Deepfake Detection (Yingjian Chen et al., arxiv 2024)

• Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets (Patrick Grommelt et al., arxiv 2024) :globe_with_meridians: :octocat:

• A Single Simple Patch is All You Need for AI-generated Image Detection (Jiaxuan Chen, arxiv 2024):octocat:

2023

• GenDet: Towards Good Generalizations for AI-Generated Image Detection (Mingjian Zhu, arxiv 2023)

• PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection (Nan Zhong et al., arxiv 2023) :globe_with_meridians: :octocat:

Back to TOC ↑

Tools

• SIDBench: A Python framework for reliably assessing synthetic image detection methods (Manos Schinas et al., MAD Workshop 2024) :octocat:

• PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection (Nan Zhong et al., arxiv 2023) :globe_with_meridians: :octocat:

Back to TOC ↑

Citing Awesome AI-generated Image Detection

If you find this project useful for your research, please use the following BibTeX entry.

@article{diao2024vulnerabilities,
  title={Vulnerabilities in ai-generated image detection: The challenge of adversarial attacks},
  author={Diao, Yunfeng and Zhai, Naixin and Miao, Changtao and Yu, Zitong and Wei, Xingxing and Yang, Xun and Wang, Meng},
  journal={arXiv preprint arXiv:2407.20836},
  year={2024}
}

Acknowledgments

The list is inspired by Awesome Dataset Distillation and Awesome-Deepfakes-Detection. Thanks for their great work!