基于扩散模型的生成式图像检测综述

doi:10.19678/j.issn.1000-3428.0253234

摘要/Abstract

摘要： 近年来,基于扩散模型(DM)的生成式图像技术取得了突破性进展,以Stable Diffusion、DALL-E和Midjourney为代表的文生图模型已经广泛应用于商业领域和日常生活。然而,高度逼真的AI生成图像也带来了图像真实性挑战,催生了虚假信息传播、版权侵犯等社会问题。为有效应对这些挑战,本文系统综述了基于扩散模型的生成图像检测技术的最新研究进展。首先,梳理了扩散模型从原理、基础框架到大规模应用的发展。其次,总结数据集发展,指出数据集建设正从少量生成器、低分辨率向多模型融合、高质量多级筛选方向发展。再次,分析了检测技术的三大主流方法:基于隐式特征的检测技术、基于显式特征的检测技术以及基于混合特征的检测技术。最后,分析了当前检测技术面临的主要挑战,并展望了未来研究方向。本综述为研究人员和从业者提供了全面的技术图谱和发展趋势参考。

关键词: 扩散模型, 文生图, 生成图像, 生成图像伪影, 生成图像检测

Abstract: In recent years, generative image technology based on Diffusion Models (DMs) has made breakthroughs, with text-to-image models represented by Stable Diffusion, DALL-E, and Midjourney have been widely applied in commercial sectors and everyday life. However, highly realistic artificial intelligence-generated images have also brought challenges to image authenticity, giving rise to social issues such as the spread of misinformation and copyright infringement. To address these challenges effectively, this paper systematically reviews the latest research progress in detection technologies for images generated by DMs. First, it outlines the development trajectory of DMs based on their principles and fundamental frameworks for large-scale applications. Second, it summarizes the evolution of dataset construction, indicating that dataset development is progressing from using few generators and low resolutions to multi-model integration and high-quality, multi-stage filtering. Third, it analyzes three types of detection technologies: those based on implicit, explicit, and hybrid features. Finally, it analyzes the main challenges facing current detection technologies and provides an outlook on future research directions. This review offers researchers and practitioners with a comprehensive technical landscape and reference for future development trends.

Key words: Diffusion Model (DM), text-to-image, generated image, generated image artifact, generated image detection

中图分类号:

TP391.41

罗昊, 辛一冉, 唐云祁. 基于扩散模型的生成式图像检测综述[J]. 计算机工程, 2026, 52(10): 31-49.

LUO Hao, XIN Yiran, TANG Yunqi. Review of Generative Image Detection Based on Diffusion Models[J]. Computer Engineering, 2026, 52(10): 31-49.

https://www.ecice06.com/CN/Y2026/V52/I10/31

参考文献

[1] XU Q, CHEN D, CHEN J, et al. Recent advances on generalizable diffusion-generated image detection[EB/OL]. [2025-10-16]. http://arxiv.org/abs/2502.19716.
[2] MAHARA A, RISHE N. Methods and trends in detecting AI-generated images: a comprehensive review[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2502.15176.
[3] 刘晓龙, 刘欢, 赵耀, 等. AIGC伪造内容被动检测与主动防御技术综述[J]. 中国科学(信息科学), 2025, 55(9): 2250-2288. LIU X L, LIU H, ZHAO Y, et al. Review of AIGC passive detection and proactive protection[J]. Scientia Sinica (Informationis), 2025, 55(9): 2250-2288. (in Chinese)
[4] 程泊宣, 李明轩, 张正宇. 扩散模型生成式图像检测技术研究综述[J]. 计算机工程与应用, 2025, 61(20): 1-18. CHENG B X, LI M X, ZHANG Z Y. Review of generative image detection technology based on diffusion[J]. Computer Engineering and Applications, 2025, 61(20): 1-18. (in Chinese)
[5] SOHL-DICKSTEIN J, WEISS E A, MAHESWARANATHAN N, et al. Deep unsupervised learning using nonequilibrium thermodynamics[EB/OL]. [2025-10-16]. https://arxiv.org/abs/1503.03585.
[6] HO J, JAIN A, ABBEEL P. Denoising diffusion probabilistic models[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2006.11239.
[7] SONG Y, SOHL-DICKSTEIN J, KINGMA D P, et al. Score-based generative modeling through stochastic differential equations[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2011.13456.
[8] SONG J M, MENG C L, ERMON S. Denoising diffusion implicit models[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2010.02502.
[9] NICHOL A, DHARIWAL P. Improved denoising diffusion probabilistic models[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2102.09672.
[10] DHARIWAL P, NICHOL A. Diffusion models beat GANs on image synthesis[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2105.05233.
[11] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//Proceedigns of Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2015: 234-241.
[12] ROMBACH R, BLATTMANN A, LORENZ D, et al. High-resolution image synthesis with latent diffusion models[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2022: 10674-10685.
[13] NICHOL A, DHARIWAL P, RAMESH A, et al. GLIDE: towards photorealistic image generation and editing with text-guided diffusion models[C]//Proceedings of the 39th International Conference on Machine Learning. [S. l.]: PMLR, 2022: 16784-16804.
[14] CHITWAN S, CHAN W, SAXENA S, et al. Photorealistic text-to-image diffusion models with deep language understanding[J]. Advances in Neural Information Processing Systems, 2022, 35: 36479-36494.
[15] HO J, SALIMANS T. Classifier-free diffusion guidance[EB/OL]. [EB/OL]. [2025-10-16]. https://arxiv.org/abs/2207.12598.
[16] MENG C L, HE Y T, SONG Y, et al. SDEdit: guided image synthesis and editing with stochastic differential equations[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2108.01073.
[17] KAWAR B, ELAD M, ERMON S, et al. Denoising diffusion restoration models[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2201.11793.
[18] SAHARIA C, HO J, CHAN W, et al. Image super-resolution via iterative refinement[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(4): 4713-4726.
[19] LUGMAYR A, DANELLJAN M, ROMERO A, et al. RePaint: inpainting using denoising diffusion probabilistic models[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2022: 11451-11461.
[20] CHOI J, KIM S, JEONG Y, et al. ILVR: conditioning method for denoising diffusion probabilistic models[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2022: 14347-14356.
[21] RAMESH A, DHARIWAL P, NICHOL A, et al. Hierarchical text-conditional image generation with CLIP latents[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2204.06125.
[22] GROMMELT P, WEISS L, PFREUNDT F J, et al. Fake or JPEG? Revealing common biases in generated image detection datasets[C]//Proceedings of the ECCV 2024. Berlin, Germany: Springer, 2025: 80-95.
[23] ZHU M J, CHEN H T, YAN Q Y, et al. GenImage: a million-scale benchmark for detecting AI-generated image[C]//Proceedings of the Advances in Neural Information Processing Systems 36. New Orleans, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2023: 77771-77782.
[24] RAJAN A S, OJHA U, SCHLOESSER J, et al. Aligned datasets improve detection of latent diffusion-generated images[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2410.11835.
[25] GUILLARO F, ZINGARINI G, USMAN B, et al. A bias-free training paradigm for more general AI-generated image detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2025: 18685-18694.
[26] CHEN R X, XI J W, YAN Z Y, et al. Dual data alignment makes AI-generated image detector easier generalizable[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2505.14359.
[27] WANG L, CHEN W, LI Z, et al. PDA: generalizable detection of AI-generated images via post-hoc distribution alignment[EB/OL]. [2025-10-16]. https://arxiv.org/html/2502.10803v1.
[28] DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2009: 248-255.
[29] BROCK A, DONAHUE J, SIMONYAN K. Large scale GAN training for high fidelity natural image synthesis[EB/OL]. [2025-10-16]. https://arxiv.org/abs/1809.11096.
[30] GU S Y, CHEN D, BAO J M, et al. Vector quantized diffusion model for text-to-image synthesis[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2022: 10686-10696.
[31] WANG Z D, BAO J M, ZHOU W G, et al. DIRE for diffusion-generated image detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2023: 22388-22398.
[32] LIU L P, REN Y, LIN Z J, et al. Pseudo numerical methods for diffusion models on manifolds[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2202.09778.
[33] OJHA U, LI Y H, LEE Y J. Towards universal fake image detectors that generalize across generative models[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2023: 24480-24489.
[34] KARRAS T, AILA T, LAINE S, et al. Progressive growing of GANs for improved quality, stability, and variation[EB/OL]. [2025-10-16].https://arxiv.org/abs/1710.10196.
[35] KARRAS T, LAINE S, AILA T M. A style-based generator architecture for generative adversarial networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2019: 4396-4405.
[36] ZHU J Y, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2017: 2242-2251.
[37] CHOI Y, CHOI M, KIM M, et al. StarGAN: unified generative adversarial networks for multi-domain image-to-image translation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2018: 8789-8797.
[38] PARK T, LIU M Y, WANG T C, et al. Semantic image synthesis with spatially-adaptive normalization[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 2332-2341.
[39] CHEN Q F, KOLTUN V. Photographic image synthesis with cascaded refinement networks[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2017: 1520-1529.
[40] LI K, ZHANG T H, MALIK J. Diverse image synthesis from semantic layouts via conditional IMLE[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2019: 4219-4228.
[41] DAI T, CAI J R, ZHANG Y B, et al. Second-order attention network for single image super-resolution[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 11057-11066.
[42] CHEN C, CHEN Q F, XU J, et al. Learning to see in the dark[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D.C., USA: IEEE Press, 2018: 3291-3300.
[43] ROSSLER A, COZZOLINO D, VERDOLIVA L, et al. FaceForensics++: learning to detect manipulated facial images[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2019: 1-11.
[44] CHEN Z X, SUN K, ZHOU Z Y, et al. DiffusionFace: towards a comprehensive dataset for diffusion-based face forgery analysis[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2403.18471.
[45] LU Z Y, HUANG D, BAI L, et al. Seeing is not always believing: benchmarking human and model perception of AI-generated images[C]//Proceedings of the Advances in Neural Information Processing Systems 36. New Orleans, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2023: 25435-25447.
[46] KANG H, WEN S, WEN Z, et al. LEGION: learning to ground and explain for synthetic image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2503.15264.
[47] LIANG Y, HE J, LI G, et al. Rich human feedback for text-to-image generation[EB/OL]//Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 19401-19411.
[48] YAN S L, LI O X, CAI J Y, et al. A sanity check for AI-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2406.19435.
[49] HUANG Z C, XIA B, LIN Z C, et al. FFAA: multimodal large language model based explainable open-world face forgery analysis assistant[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2408.10072.
[50] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[EB/OL]. [2025-10-16]. https://arxiv.org/abs/1512.03385.
[51] WANG P, BAI S, TAN S N, et al. Qwen2-VL: enhancing vision-language model’s perception of the world at any resolution[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2409.12191.
[52] HUANG Z L, HU J W, LI X T, et al. SIDA: social media image deepfake detection, localization and explanation with large multimodal model[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2025: 28831-28841.
[53] SARKAR A, MAI H L, MAHAPATRA A, et al. Shadows don’t lie and lines can’t bend! Generative models don’t know projective geometry…for now[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 28140-28149.
[54] LI J N, LI D X, XIONG C M, et al. BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation[C]//Proceedings of the International Conference on Machine Learning. Washington D.C., USA: IEEE Press, 2022: 12888-12900.
[55] PODELL D, ENGLISH Z, LACEY K, et al. SDXL: improving latent diffusion models for high-resolution image synthesis[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2307.01952.
[56] ARKHIPKIN V, FILATOV A, VASILEV V, et al. Kandinsky 3.0 technical report[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2312.03511.
[57] CHEN J S, YU J C, GE C J, et al. PixArt-α: fast training of diffusion transformer for photorealistic text-to-image synthesis[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2310.00426.
[58] HONG Y, ZHANG J F. WildFake: a large-scale challenging dataset for AI-generated images detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2402.11843.
[59] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[EB/OL]. [2025-10-16]. https://arxiv.org/abs/1405.0312.
[60] YU F, SEFF A, ZHANG Y D, et al. LSUN: construction of a large-scale image dataset using deep learning with humans in the loop[EB/OL]. [2025-10-16]. https://arxiv.org/abs/1506.03365.
[61] SCHUHMANN C, BEAUMONT R, VENCU R, et al. LAION-5B: an open large-scale dataset for training next generation image-text models[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2210.08402.
[62] ZHOU Z Y, LUO Y P, WU Y C, et al. AIGI-Holmes: towards explainable and generalizable AI-generated image detection via multimodal large language models[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2025: 18746-18758.
[63] PARK J, OWENS A. Community Forensics: using thousands of generators to train fake image detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2025: 8245-8257.
[64] LIU Z W, LUO P, WANG X G, et al. Deep learning face attributes in the wild[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2016: 3730-3738.
[65] VASILCOIU A, NAJDENKOSKA I, GERADTS Z, et al. LATTE: latent trajectory embedding for diffusion-generated image detection[EB/OL]. https://ui.adsabs.harvard.edu/abs/2025arXiv250703054V/abstract.
[66] 马静, 车进, 孙末贤. 融合Transformer与DF-GAN的文本生成图像方法[J]. 计算机工程, 2026, 52(2): 413-422. MA J, CHE J, SUN M X. Text-to-image generation method combining Transformer and DF-GAN[J]. Computer Engineering, 2026, 52(2): 413-422. (in Chinese)
[67] 张汝波, 蔺庆龙, 张天一. 基于深度学习的图像篡改检测方法综述[J]. 智能系统学报, 2025, 20(2): 283-304. ZHANG R B, LIN Q L, ZHANG T Y. A review of image tampering detection methods based on deep learning[J]. CAAI Transactions on Intelligent Systems, 2025, 20(2): 283-304. (in Chinese)
[68] EPSTEIN D C, JAIN I, WANG O, et al. Online detection of AI-generated images[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Washington D.C., USA: IEEE Press, 2023: 382-392.
[69] LU Z Y, HUANG D, BAI L, et al. Seeing is not always believing: benchmarking human and model perception of AI-generated images[C]//Proceedings of the Advances in Neural Information Processing Systems 36. New Orleans, USA. Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2023: 25435-25447.
[70] ZHU M J, CHEN H T, YAN Q Y, et al. GenImage: a million-scale benchmark for detecting AI-generated image[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2306.08571.
[71] RICKER J, DAMM S, HOLZ T, et al. Towards the detection of diffusion model deepfakes[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2210.14571.
[72] BIRD J J, LOTFI A. CIFAKE: image classification and explainable identification of AI-generated synthetic images[J]. IEEE Access, 2024, 12: 15642-15650.
[73] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16×16 words: Transformers for image recognition at scale[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2010.11929.
[74] COCCOMINI D A, ESULI A, FALCHI F, et al. Detecting images generated by diffusers[J]. PeerJ Computer Science, 2024, 10: e2127.
[75] DAS S, DUTTA D, GHOSH T, et al. Universal detection and source attribution of diffusion model generated images with high generalization and robustness[M]//MAJI P, HUANG T, PAL N R, et al. Pattern recognition and machine intelligence. Berlin, Germany: Springer, 2023: 441-448.
[76] ZHU M J, CHEN H T, HUANG M X, et al. GenDet: towards good generalizations for AI-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2312.08880.
[77] HE Z Y, CHEN P Y, HO T Y. RIGID: a training-free and model-agnostic framework for robust AI-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2405.20112.
[78] OQUAB M, DARCET T, MOUTAKANNI T, et al. DINOv2: learning robust visual features without supervision[EB/OL]. [2025-10-16]. https://arxiv.org/pdf/2304.07193.
[79] XU K, ZHANG L, SHI J. Detecting image attribution for text-to-image diffusion models in RGB and beyond[EB/OL]. [2025-10-16]. https://arxiv.org/html/2403.19653v1.
[80] YAN S L, LI O X, CAI J Y, et al. A sanity check for AI-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2406.19435.
[81] RADFORD A, KIM J W, HALLACY C, et al. Learning transferable visual models from natural language supervision[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2103.00020.
[82] SHA Z Y, LI Z, YU N, et al. DE-FAKE: detection and attribution of fake images generated by text-to-image generation models[C]//Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security. New York, USA: ACM Press, 2023: 3418-3432.
[83] LIU Z H, WANG H Y, KANG Y Y, et al. Mixture of low-rank experts for transferable AI-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2404.04883.
[84] HU E J, SHEN Y L, WALLIS P, et al. LoRA: low-rank adaptation of large language models[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2106.09685.
[85] KHAN S A, DANG-NGUYEN D T. CLIPping the deception: adapting vision-language models for universal deepfake detection[C]// Proceedings of the 2024 International Conference on Multimedia Retrieval. New York, USA: ACM Press, 2024: 1006-1015.
[86] COZZOLINO D, POGGI G, CORVI R, et al. Raising the bar of AI-generated image detection with CLIP[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2312.00195.
[87] GAINTSEVA T, KUSHNAREVA L, MAGAI G, et al. Improving interpretability and robustness for the detection of AI-generated images[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2406.15035.
[88] SHEN Z, ZHANG K, JIA B, et al. DF-LLaVA: unlocking MLLM’s potential for synthetic image detection via prompt-guided knowledge injection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2509.14957.
[89] CHANG Y M, YEH C, CHIU W C, et al. AntifakePrompt: prompt-tuned vision-language models are fake image detectors[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2310.17419.
[90] EUTAMENE H B, HAMIDOUCHE W, KEITA M, et al. SIREN: self-improving retrieval-augmented deepfake detection with explainable LLM reasoning[EB/OL]. [2025-10-16]. https://ssrn.com/abstract=5492126.
[91] CHEN J X, YAO J T, NIU L. A single simple patch is all you need for AI-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2402.01123.
[92] YUAN L, LI X, ZHANG Y, et al. MLEP: multi-granularity local entropy patterns for generalized ai-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2504.13726.
[93] WONG Y J, NG T K. Local statistics for generative image detection[EB/OL]. [2025-10-16]. https://arxiv.org/html/2310.16684v2.
[94] ZHANG J H, LI L, YAN C G, et al. Frequency-aware correlation discovering and spatial forgery clue distilling for synthetic image detection[C]//Proceedings of the 33rd ACM International Conference on Multimedia. New York, USA: ACM Press, 2025: 11726-11735.
[95] DAS D, YAHAN M, ZAMAN M T, et al. Edge-enhanced vision transformer framework for accurate AI-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2508.17877.
[96] JU Y, JIA S, CAI J L, et al. GLFF: global and local feature fusion for AI-synthesized image detection[J]. IEEE Transactions on Multimedia, 2024, 26: 4073-4085.
[97] UHLENBROCK L, COZZOLINO D, MOUSSA D, et al. Did you note my palette? Unveiling synthetic images through color statistics[C]//Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security. New York, USA: ACM Press, 2024: 47-52.
[98] DOGOULIS P, KORDOPATIS-ZILOS G, KOMPATSIARIS I, et al. Improving synthetically generated image detection in cross-concept settings[C]//Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation. New York, USA: ACM Press, 2023: 28-35.
[99] CHENG H, GUO Y Y, WANG T Y, et al. Diffusion facial forgery detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2401.15859.
[100] ZHONG N, XU Y R, LI S, et al. PatchCraft: exploring texture patch for efficient AI-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2311.12397.
[101] LU Y H, EBRAHIMI T. Towards the detection of AI-synthesized human face images[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2402.08750.
[102] DOLORIEL C T, CHEUNG N M. Frequency masking for universal deepfake detection[C]//Proceedings of 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Washington D.C., USA: IEEE Press, 2024: 1-10.
[103] KOUTLIS C, PAPADOPOULOS S. Leveraging representations from intermediate encoder-blocks for synthetic image detection[C]//Proceedings of the ECCV 2024. Berlin, Germany: Springer, 2025: 394-411.
[104] BARU L B, BODDEDA R, PATEL S A, et al. Wavelet-driven generalizable framework for deepfake face forgery detection[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW). Washington D.C., USA: IEEE Press, 2025: 1576-1584.
[105] LANZINO R, FONTANA F, DIKO A, et al. Faster than lies: real-time deepfake detection using binary neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Washington D.C., USA: IEEE Press, 2024: 3771-3780.
[106] KARAGEORGIOU D, PAPADOPOULOS S, KOMPATSIARIS I, et al. Any-resolution AI-generated image detection by spectral learning[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2025: 18706-18717.
[107] ZHANG D C, ZHANG T, GE S M, et al. Enhancing frequency forgery clues for diffusion-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2511.00429.
[108] ZHANG D, ZHANG T, GE S, et al. Leveraging natural frequency deviation for diffusion-generated image detection[EB/OL]. [2025-10-16]. https://openreview.net/forum?id=fPBExgC1m9&referrer=%5Bthe%20profile%20of%20Sabine%20S%C3%BCsstrunk%5D%28%2Fprofile%3Fid%3D~Sabine_S%C3%BCsstrunk1%29.
[109] ZHOU C M, WANG J A, LI Y, et al. Beyond semantic features: pixel-level mapping for generalized AI-generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2512.17350.
[110] WEN Y, KIRCHENBAUER J, GEIPING J, et al. Tree-Ring watermarks: fingerprints for diffusion images that are invisible and robust[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2305.20030.
[111] DURALL R, KEUPER M, KEUPER J. Watch your up-convolution: CNN based generative deep neural networks are failing to reproduce spectral distributions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2020: 7887-7896.
[112] CORVI R, COZZOLINO D, POGGI G, et al. Intriguing properties of synthetic images: from generative adversarial networks to diffusion models[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Washington D.C., USA: IEEE Press, 2022: 973-982.
[113] LIU H, TAN Z C, TAN C C, et al. Forgery-aware adaptive transformer for generalizable synthetic image detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 10770-10780.
[114] WIßMANN A, ZEILER S, NICKEL R M, et al. Whodunit: detection and attribution of synthetic images by leveraging model-specific fingerprints[C]//Proceedings of the 3rd ACM International Workshop on Multimedia AI against Disinformation. New York, USA: ACM Press, 2024: 65-72.
[115] MENG Z L, PENG B, DONG J, et al. Artifact feature purification for cross-domain detection of AI-generated images[J]. Computer Vision and Image Understanding, 2024, 247: 104078.
[116] RICKER J, LUKOVNIKOV D, FISCHER A. AEROBLADE: training-free detection of latent diffusion images using autoencoder reconstruction error[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 9130-9140.
[117] MA R P, DUAN J H, KONG F, et al. Exposing the fake: effective diffusion-generated images detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2307.06272.
[118] LUO Y P, DU J L, YAN K, et al. LaRE²: latent reconstruction error based method for diffusion-generated image detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 1-15.
[119] CHU B L, XU X, WANG X, et al. FIRE: robust detection of diffusion-generated images via frequency-guided reconstruction error[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2025: 12830-12839.
[120] LIANG Y, YU M, LI G, et al. Denoising trajectory biases for zero-shot ai-generated image detection[C]//Proceedings of the 39th Annual Conference on Neural Information Processing Systems. New Orleans, USA: Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2025: 1-17.
[121] SINITSA S, FRIED O. Deep image fingerprint: towards low budget synthetic image detection and model lineage analysis[C]//Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). Washington D.C., USA: IEEE Press, 2024: 4055-4064.
[122] TAN C C, LIU H, ZHAO Y, et al. Rethinking the up-sampling operations in CNN-based generative network for generalizable deepfake detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 28130-28139.
[123] CAZENAVETTE G, SUD A, LEUNG T, et al. FakeInversion: learning to detect images from unseen text-to-image models by inverting stable diffusion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2024: 10759-10769.
[124] ZHANG Y C, XU X G. Diffusion noise feature: accurate and fast generated image detection[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2312.02625.
[125] CHEN B Y, ZENG J S, YANG J Q, et al. DRCT: diffusion reconstruction contrastive training towards universal detection of diffusion generated images[C]//Proceedings of the International Conference on Machine Learning. [S. l.]: PMLR, 2024:7621-7639.
[126] CORVI R, COZZOLINO D, ZINGARINI G, et al. On the detection of synthetic images generated by diffusion models[EB/OL]. [2025-10-16]. https://arxiv.org/abs/2211.00680.
[127] ZHANG H F, HE Q H, BI X L, et al. Towards universal AI-generated image detection by variational information bottleneck network[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2025: 23828-23837.
[128] JIA Z X, HUANG C W, ZHU Y S, et al. Secret lies in color: enhancing AI-generated images detection with color distribution analysis[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2025: 13445-13454.

选择文件类型/文献管理软件名称

选择包含的内容