{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T01:42:59Z","timestamp":1775785379883,"version":"3.50.1"},"reference-count":113,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["MRI20 CNS-2018611"],"award-info":[{"award-number":["MRI20 CNS-2018611"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["MRI CNS-1920182"],"award-info":[{"award-number":["MRI CNS-1920182"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Science Review"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.cosrev.2026.100908","type":"journal-article","created":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T14:40:41Z","timestamp":1769006441000},"page":"100908","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":4,"special_numbering":"C","title":["Methods and trends in detecting AI-generated images: A comprehensive review"],"prefix":"10.1016","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5831-3552","authenticated-orcid":false,"given":"Arpan","family":"Mahara","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1611-4067","authenticated-orcid":false,"given":"Naphtali","family":"Rishe","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.cosrev.2026.100908_bib0010","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/T-C.1974.223784","article-title":"Discrete cosine transform","volume":"100","author":"Ahmed","year":"1974","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/j.cosrev.2026.100908_bib0015","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/OJSP.2023.3337714","article-title":"Synthbuster: towards detection of diffusion model generated images","volume":"5","author":"Bammey","year":"2024","journal-title":"IEEE Open J. Signal Process."},{"issue":"10","key":"10.1016\/j.cosrev.2026.100908_bib0020","doi-asserted-by":"crossref","first-page":"199","DOI":"10.3390\/jimaging9100199","article-title":"AI VS. AI: can AI detect AI-generated images?","volume":"9","author":"Baraheem","year":"2023","journal-title":"J. Imaging"},{"key":"10.1016\/j.cosrev.2026.100908_bib0025","series-title":"The Analytical Theory of Heat","author":"Fourier","year":"2003"},{"key":"10.1016\/j.cosrev.2026.100908_bib0030","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3356122","article-title":"CIFAKE: image classification and explainable identification of AI-generated synthetic images","author":"Bird","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.cosrev.2026.100908_bib0035","author":"Boychev"},{"key":"10.1016\/j.cosrev.2026.100908_bib0040","author":"Brock"},{"key":"10.1016\/j.cosrev.2026.100908_bib0045","author":"Cao"},{"key":"10.1016\/j.cosrev.2026.100908_bib0050","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference Proceedings, Part XXVI, August 23\u201328","first-page":"103","article-title":"What makes fake images detectable? Understanding properties that generalize","author":"Chai","year":"2020"},{"key":"10.1016\/j.cosrev.2026.100908_bib0055","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3291","article-title":"Learning to see in the dark","author":"Chen","year":"2018"},{"issue":"7","key":"10.1016\/j.cosrev.2026.100908_bib0060","article-title":"IPD-Net: detecting AI-generated images via Inter-Patch dependencies","volume":"15","author":"Chen","year":"2024","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"10.1016\/j.cosrev.2026.100908_bib0065","author":"Chen"},{"key":"10.1016\/j.cosrev.2026.100908_bib0070","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"1511","article-title":"Photographic image synthesis with cascaded refinement networks","author":"Chen","year":"2017"},{"key":"10.1016\/j.cosrev.2026.100908_bib0075","series-title":"International Conference on Machine Learning. PMLR","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.cosrev.2026.100908_bib0080","series-title":"2008 IEEE 10th Workshop on Multimedia Signal Processing","first-page":"803","article-title":"Image tampering detection by blocking periodicity analysis in JPEG compressed images","author":"Chen","year":"2008"},{"key":"10.1016\/j.cosrev.2026.100908_bib0085","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"8789","article-title":"StarGAN: unified generative adversarial networks for multi-domain image-to-image translation","author":"Choi","year":"2018"},{"key":"10.1016\/j.cosrev.2026.100908_bib0090","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions","author":"Chollet","year":"2017"},{"issue":"90","key":"10.1016\/j.cosrev.2026.100908_bib0095","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1090\/S0025-5718-1965-0178586-1","article-title":"An algorithm for the machine calculation of complex Fourier series","volume":"19","author":"Cooley","year":"1965","journal-title":"Math. Comp."},{"key":"10.1016\/j.cosrev.2026.100908_bib0100","series-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"On the detection of synthetic images generated by diffusion models","author":"Corvi","year":"2023"},{"key":"10.1016\/j.cosrev.2026.100908_bib0105","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4356","article-title":"Raising the bar of AI-generated image detection with CLIP","author":"Cozzolino","year":"2024"},{"key":"10.1016\/j.cosrev.2026.100908_bib0110","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1109\/TIFS.2019.2916364","article-title":"Noiseprint: a CNN-based camera model fingerprint","volume":"15","author":"Cozzolino","year":"2019","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.cosrev.2026.100908_bib0115","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11065","article-title":"Second-order attention network for single image super-resolution","author":"Dai","year":"2019"},{"key":"10.1016\/j.cosrev.2026.100908_bib0120","series-title":"Proceedings of the 6th ACM Multimedia Systems Conference","first-page":"219","article-title":"Raise: a raw images dataset for digital image forensics","author":"Dang-Nguyen","year":"2015"},{"key":"10.1016\/j.cosrev.2026.100908_bib0130","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100908_bib0135","author":"Dosovitskiy"},{"key":"10.1016\/j.cosrev.2026.100908_bib0140","first-page":"3022","article-title":"Fourier spectrum discrepancies in deep network generated images","volume":"33","author":"Dzanic","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.cosrev.2026.100908_bib0145","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1109\/TIFS.2012.2190402","article-title":"Rich models for steganalysis of digital images","volume":"7","author":"Fridrich","year":"2012","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.cosrev.2026.100908_bib0150","author":"Goebel"},{"key":"10.1016\/j.cosrev.2026.100908_bib0155","first-page":"27","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100908_bib0165","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10696","article-title":"Vector quantized diffusion model for text-to-image synthesis","author":"Shuyang","year":"2022"},{"issue":"1","key":"10.1016\/j.cosrev.2026.100908_bib0170","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/BF01456927","article-title":"Zur theorie DER orthogonalen funktionensysteme","volume":"71","author":"Haar","year":"1911","journal-title":"Math. Ann."},{"key":"10.1016\/j.cosrev.2026.100908_bib0175","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"Kaiming","year":"2016"},{"key":"10.1016\/j.cosrev.2026.100908_bib0180","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Jonathan","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100908_bib0185","series-title":"European Conference on Computer Vision","first-page":"76","article-title":"Fingerprintnet: synthesized fingerprints for generated image detection","author":"Jeong","year":"2022"},{"key":"10.1016\/j.cosrev.2026.100908_bib0190","doi-asserted-by":"crossref","first-page":"5875","DOI":"10.1109\/TIP.2021.3089943","article-title":"LayerCAM: exploring hierarchical class activation maps for localization","volume":"30","author":"Jiang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cosrev.2026.100908_bib0195","first-page":"3465","article-title":"Fusing global and local features for generalized AI-synthesized image detection","author":"Yan","year":"2022","journal-title":"IEEE Int. Conf. Image Process."},{"key":"10.1016\/j.cosrev.2026.100908_bib0200","author":"Karras"},{"key":"10.1016\/j.cosrev.2026.100908_bib0205","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4401","article-title":"A style-based generator architecture for generative adversarial networks","author":"Karras","year":"2019"},{"key":"10.1016\/j.cosrev.2026.100908_bib0210","first-page":"30","article-title":"LightGBM: a highly efficient gradient boosting decision tree","author":"Guolin","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100908_bib0215","author":"Kingma"},{"key":"10.1016\/j.cosrev.2026.100908_bib0220","series-title":"European Conference on Computer Vision","first-page":"394","article-title":"Leveraging representations from intermediate encoder-blocks for synthetic image detection","author":"Koutlis","year":"2025"},{"key":"10.1016\/j.cosrev.2026.100908_bib0225","unstructured":"A. Krizhevsky, Learning multiple layers of features from tiny images, Technical Report, University of Toronto, 2009."},{"key":"10.1016\/j.cosrev.2026.100908_bib0230","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4220","article-title":"Diverse image synthesis from semantic layouts via conditional IMLE","author":"Li","year":"2019"},{"key":"10.1016\/j.cosrev.2026.100908_bib0235","author":"Ouxiang"},{"key":"10.1016\/j.cosrev.2026.100908_bib0240","doi-asserted-by":"crossref","first-page":"862","DOI":"10.1109\/LSP.2021.3130525","article-title":"Detection of GAN-generated images by estimating artifact similarity","volume":"29","author":"Weichuang","year":"2022","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.cosrev.2026.100908_bib0245","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3855","article-title":"MaskSim: detection of synthetic images by masked spectrum similarity analysis","author":"Yanhao","year":"2024"},{"key":"10.1016\/j.cosrev.2026.100908_bib0250","series-title":"European Conference on Computer Vision","first-page":"95","article-title":"Detecting generated images by real images","author":"Liu","year":"2022"},{"key":"10.1016\/j.cosrev.2026.100908_bib0255","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10770","article-title":"Forgery-aware adaptive transformer for generalizable synthetic image detection","author":"Liu","year":"2024"},{"key":"10.1016\/j.cosrev.2026.100908_bib0260","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11976","article-title":"A convnet for the 2020s","author":"Liu","year":"2022"},{"key":"10.1016\/j.cosrev.2026.100908_bib0265","author":"Liu"},{"key":"10.1016\/j.cosrev.2026.100908_bib0270","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"448","article-title":"Detecting images generated by deep diffusion models using their local intrinsic dimensionality","author":"Lorenz","year":"2023"},{"key":"10.1016\/j.cosrev.2026.100908_bib0275","author":"Lorenz"},{"issue":"2","key":"10.1016\/j.cosrev.2026.100908_bib0280","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1109\/TIFS.2006.873602","article-title":"Digital camera identification from sensor pattern noise","volume":"1","author":"Lukas","year":"2006","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.cosrev.2026.100908_bib0285","first-page":"3091","article-title":"Detecting GAN-generated images by orthogonal training of multiple CNNS","author":"Mandelli","year":"2022","journal-title":"IEEE Int. Conf. Image Process."},{"key":"10.1016\/j.cosrev.2026.100908_bib0290","series-title":"2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR)","first-page":"506","article-title":"Do GANs leave artificial fingerprints?","author":"Marra","year":"2019"},{"key":"10.1016\/j.cosrev.2026.100908_bib0295","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104078","article-title":"Artifact feature purification for cross-domain detection of AI-generated images","volume":"247","author":"Meng","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.cosrev.2026.100908_bib0305","series-title":"Interdependent Human-Machine Teams","first-page":"315","article-title":"The generative AI weapon of mass destruction: evolving disinformation threats, vulnerabilities, and mitigation frameworks","author":"Mylrea","year":"2025"},{"key":"10.1016\/j.cosrev.2026.100908_bib0310","author":"Nichol"},{"key":"10.1016\/j.cosrev.2026.100908_bib0315","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"24480","article-title":"Towards universal fake image detectors that generalize across generative models","author":"Ojha","year":"2023"},{"key":"10.1016\/j.cosrev.2026.100908_bib0325","author":"Park"},{"key":"10.1016\/j.cosrev.2026.100908_bib0330","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2337","article-title":"Semantic image synthesis with spatially-adaptive normalization","author":"Park","year":"2019"},{"key":"10.1016\/j.cosrev.2026.100908_bib0335","series-title":"International Conference on Machine Learning. PMLR","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.cosrev.2026.100908_bib0340","first-page":"2200","article-title":"ArtiFact: a large-scale dataset with artificial and factual images for generalizable and robust synthetic image detection","author":"Rahman","year":"2023","journal-title":"IEEE Int. Conf. Image Process."},{"key":"10.1016\/j.cosrev.2026.100908_bib0345","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"983","article-title":"Ablation-CAM: visual explanations for deep convolutional network via gradient-free localization","author":"Ramaswamy","year":"2020"},{"key":"10.1016\/j.cosrev.2026.100908_bib0350","author":"Ramesh"},{"key":"10.1016\/j.cosrev.2026.100908_bib0355","series-title":"International Conference on Machine Learning. PMLR","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"10.1016\/j.cosrev.2026.100908_bib0360","series-title":"International Conference on Machine Learning. PMLR","first-page":"1530","article-title":"Variational inference with normalizing flows","author":"Rezende","year":"2015"},{"key":"10.1016\/j.cosrev.2026.100908_bib0365","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.cosrev.2026.100908_bib0370","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1","article-title":"FaceForensics++: learning to detect manipulated facial images","author":"Rossler","year":"2019"},{"key":"10.1016\/j.cosrev.2026.100908_bib0375","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cosrev.2026.100908_bib0380","doi-asserted-by":"crossref","DOI":"10.1016\/j.econlet.2023.111317","article-title":"Generative AI and deceptive news consumption","volume":"232","author":"Sandrini","year":"2023","journal-title":"Econ. Lett."},{"key":"10.1016\/j.cosrev.2026.100908_bib0385","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"618","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"10.1016\/j.cosrev.2026.100908_bib0390","series-title":"Digital Image Forensics","author":"Sencar","year":"2013"},{"key":"10.1016\/j.cosrev.2026.100908_bib0395","series-title":"International Conference on Machine Learning. PMLR","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015"},{"key":"10.1016\/j.cosrev.2026.100908_bib0400","author":"Song"},{"key":"10.1016\/j.cosrev.2026.100908_bib0405","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12105","article-title":"Learning on gradients: generalized artifacts representation for GAN-generated images detection","author":"Tan","year":"2023"},{"key":"10.1016\/j.cosrev.2026.100908_bib0410","series-title":"International Conference on Machine Learning. PMLR","first-page":"6105","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.cosrev.2026.100908_bib0415","series-title":"International Conference on Machine Learning. PMLR","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"Van Den Oord","year":"2016"},{"key":"10.1016\/j.cosrev.2026.100908_bib0420","first-page":"11","article-title":"Visualizing data using t-SNE","volume":"9","author":"Laurens Van der","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.cosrev.2026.100908_bib0425","series-title":"2023 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"1187","article-title":"General GAN-generated image detection by data augmentation in fingerprint domain","author":"Wang","year":"2023"},{"key":"10.1016\/j.cosrev.2026.100908_bib0430","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"24","article-title":"Score-CAM: score-weighted visual explanations for convolutional neural networks","author":"Wang","year":"2020"},{"key":"10.1016\/j.cosrev.2026.100908_bib0435","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8695","article-title":"CNN-generated images are surprisingly easy to spot for now","author":"Wang","year":"2020"},{"issue":"3","key":"10.1016\/j.cosrev.2026.100908_bib0440","first-page":"1","article-title":"Deepfake detection: a comprehensive survey from the reliability perspective","volume":"57","author":"Wang","year":"2024","journal-title":"Comput. Surv."},{"key":"10.1016\/j.cosrev.2026.100908_bib0445","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"22445","article-title":"Dire for diffusion-generated image detection","author":"Wang","year":"2023"},{"key":"10.1016\/j.cosrev.2026.100908_bib0450","author":"Haiwei"},{"key":"10.1016\/j.cosrev.2026.100908_bib0460","author":"Yan"},{"key":"10.1016\/j.cosrev.2026.100908_bib0465","author":"Yang"},{"issue":"10","key":"10.1016\/j.cosrev.2026.100908_bib0470","doi-asserted-by":"crossref","first-page":"7991","DOI":"10.1007\/s00521-022-06902-5","article-title":"Fake visual content detection using two-stream convolutional neural networks","volume":"34","author":"Yousaf","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"10.1016\/j.cosrev.2026.100908_bib0475","author":"Fisher"},{"key":"10.1016\/j.cosrev.2026.100908_bib0480","author":"Zhang"},{"issue":"7","key":"10.1016\/j.cosrev.2026.100908_bib0485","doi-asserted-by":"crossref","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","article-title":"Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cosrev.2026.100908_bib0490","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1016\/j.jvcir.2018.12.022","article-title":"A survey on image tampering and its detection in real-world photos","volume":"58","author":"Zheng","year":"2019","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.cosrev.2026.100908_bib0495","author":"Zhong"},{"key":"10.1016\/j.cosrev.2026.100908_bib0500","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2223","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"},{"key":"10.1016\/j.cosrev.2026.100908_bib0505","author":"Zhu"},{"key":"10.1016\/j.cosrev.2026.100908_bib0510","article-title":"GenImage: a million-scale benchmark for detecting ai-generated image","volume":"36","author":"Zhu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100908_bib0515","author":"Achiam"},{"key":"10.1016\/j.cosrev.2026.100908_bib0520","author":"Bai"},{"key":"10.1016\/j.cosrev.2026.100908_bib0525","author":"Cao"},{"key":"10.1016\/j.cosrev.2026.100908_bib0530","author":"Choi"},{"key":"10.1016\/j.cosrev.2026.100908_bib0535","series-title":"European Conference on Computer Vision","first-page":"54","article-title":"Zero-shot detection of ai-generated images","author":"Cozzolino","year":"2024"},{"key":"10.1016\/j.cosrev.2026.100908_bib0540","series-title":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","first-page":"122","article-title":"Fake-GPT: detecting fake image via large language model","author":"Fan","year":"2024"},{"key":"10.1016\/j.cosrev.2026.100908_bib0545","author":"He"},{"key":"10.1016\/j.cosrev.2026.100908_bib0550","author":"Huang"},{"key":"10.1016\/j.cosrev.2026.100908_bib0555","author":"Ji"},{"key":"10.1016\/j.cosrev.2026.100908_bib0560","author":"Ji"},{"key":"10.1016\/j.cosrev.2026.100908_bib0565","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cosrev.2026.100908_bib0570","author":"Oquab"},{"key":"10.1016\/j.cosrev.2026.100908_bib0575","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9130","article-title":"AEROBLADE: training-free detection of latent diffusion images using autoencoder reconstruction error","author":"Ricker","year":"2024"},{"key":"10.1016\/j.cosrev.2026.100908_bib0580","author":"Tan"},{"key":"10.1016\/j.cosrev.2026.100908_bib0585","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"key":"10.1016\/j.cosrev.2026.100908_bib0590","author":"Zhou"},{"key":"10.1016\/j.cosrev.2026.100908_bib0595","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"28130","article-title":"Rethinking the up-sampling operations in CNN-based generative network for generalizable deepfake detection","author":"Tan","year":"2024"}],"container-title":["Computer Science Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574013726000171?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1574013726000171?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:29:53Z","timestamp":1773988193000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1574013726000171"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":113,"alternative-id":["S1574013726000171"],"URL":"https:\/\/doi.org\/10.1016\/j.cosrev.2026.100908","relation":{},"ISSN":["1574-0137"],"issn-type":[{"value":"1574-0137","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Methods and trends in detecting AI-generated images: A comprehensive review","name":"articletitle","label":"Article Title"},{"value":"Computer Science Review","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cosrev.2026.100908","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"100908"}}