{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T21:16:39Z","timestamp":1770066999719,"version":"3.49.0"},"reference-count":50,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":305,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372334"],"award-info":[{"award-number":["62372334"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1805400"],"award-info":[{"award-number":["2020YFB1805400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Intelligent Systems"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:p>The proliferation of photorealistic images synthesized by generative adversarial networks (GANs) has posed serious threats to society. Therefore a new challenge task, named image attribution, is arising to attribute fake images to a specific GAN. However, existing approaches focus on model\u2010specific features but neglect the misguidance of semantic\u2010relevant features in image attribution, which leads to a significant performance decrease in cross\u2010dataset evaluation. To tackle the above problem, we propose a semantic\u2010agnostic fake image attribution (SFIA) method, which effectively distinguishes fake images by disentangling the GANs fingerprint and semantic\u2010relevant features in latent space. Specifically, we design a semantic eliminator based on residual block with skip connections that take images as input and outputs GAN fingerprint features. A classifier with an attention module for feature refinement is introduced to make the final decision. In addition, we develop a well\u2010trained reconstructor and classifier which supervise the semantic eliminator to achieve semantic\u2010agnostic feature extraction. Moreover, we propose an improved data augmentation combined with meta\u2010learning to enhance the model\u2019s generalization in detecting unseen image categories. Comprehensive experiments on various datasets, namely, CelebA, LSUN\u2010church, and LSUN\u2010bedroom, demonstrate the effectiveness of our proposed SFIA. It achieves over 95% accuracy on three datasets and exhibits superior performance in terms of generalization to unseen data.<\/jats:p>","DOI":"10.1155\/2024\/7950247","type":"journal-article","created":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T16:05:02Z","timestamp":1730477102000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SFIA: Toward a Generalized Semantic\u2010Agnostic Method for Fake Image Attribution"],"prefix":"10.1155","volume":"2024","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4893-3665","authenticated-orcid":false,"given":"Jianpeng","family":"Ke","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8085-1312","authenticated-orcid":false,"given":"Lina","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9730-7110","authenticated-orcid":false,"given":"Jiatong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7081-7150","authenticated-orcid":false,"given":"Jie","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2024,11]]},"reference":[{"key":"e_1_2_12_1_2","article-title":"Generative Adversarial Nets","volume":"27","author":"Goodfellow I.","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_2_2","doi-asserted-by":"crossref","unstructured":"KarrasT. LaineS. andAilaT. A Style-Based Generator Architecture for Generative Adversarial Networks Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition December 2019 Washington DC 4401\u20134410.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_2_12_3_2","doi-asserted-by":"crossref","unstructured":"KarrasT. LaineS. AittalaM. HellstenJ. LehtinenJ. andAilaT. Analyzing and Improving the Image Quality of Stylegan Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2020 Seattle WA 8110\u20138119.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_2_12_4_2","unstructured":"KarrasT. AilaT. LaineS. andLehtinenJ. Progressive Growing of Gans for Improved Quality Stability and Variation 2017."},{"key":"e_1_2_12_5_2","unstructured":"CirilloS. DesiatoD. ScaleraM. SolimandoG.et al. A Visual Privacy Tool to Help Users in Preserving Social Network Data IS-EUD Workshops June 2023 Cagliari Italy."},{"key":"e_1_2_12_6_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-022-00566-7"},{"key":"e_1_2_12_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102128"},{"key":"e_1_2_12_8_2","unstructured":"LiY.andLyuS. Exposing Deepfake Videos by Detecting Face Warping Artifacts 2018."},{"key":"e_1_2_12_9_2","doi-asserted-by":"crossref","unstructured":"HaliassosA. VougioukasK. PetridisS. andPanticM. Lips Don\u2019t Lie: A Generalisable and Robust Approach to Face Forgery Detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2021 Nashville TN 5039\u20135049.","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"e_1_2_12_10_2","doi-asserted-by":"crossref","unstructured":"SchwarczS.andChellappaR. Finding Facial Forgery Artifacts With Parts-Based Detectors Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2021 Nashville TN 933\u2013942.","DOI":"10.1109\/CVPRW53098.2021.00104"},{"key":"e_1_2_12_11_2","doi-asserted-by":"crossref","unstructured":"DurallR. KeuperM. andKeuperJ. Watch Your Up-Convolution: Cnn Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2020 Seattle WA 7890\u20137899.","DOI":"10.1109\/CVPR42600.2020.00791"},{"key":"e_1_2_12_12_2","unstructured":"FrankJ. EisenhoferT. Sch\u00f6nherrL. FischerA. KolossaD. andHolzT. Leveraging Frequency Analysis for Deep Fake Image Recognition International Conference on Machine Learning July 2020 PMLR 3247\u20133258."},{"key":"e_1_2_12_13_2","doi-asserted-by":"crossref","unstructured":"LiJ. XieH. LiJ. WangZ. andZhangY. Frequency-Aware Discriminative Feature Learning Supervised by Single-Center Loss for Face Forgery Detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2021 Nashville TN 6458\u20136467.","DOI":"10.1109\/CVPR46437.2021.00639"},{"key":"e_1_2_12_14_2","doi-asserted-by":"crossref","unstructured":"QianY. YinG. ShengL. ChenZ. andShaoJ. Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues European Conference on Computer Vision August 2020 Glasgow UK Springer 86\u2013103.","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"e_1_2_12_15_2","doi-asserted-by":"crossref","unstructured":"ChenP. LiuJ. LiangT.et al. Fsspotter: Spotting Face-Swapped Video by Spatial and Temporal Clues 2020 IEEE International Conference on Multimedia and Expo (ICME) July 2020 London UK IEEE 1\u20136.","DOI":"10.1109\/ICME46284.2020.9102914"},{"key":"e_1_2_12_16_2","doi-asserted-by":"crossref","unstructured":"WuX. XieZ. GaoY. andXiaoY. Sstnet: Detecting Manipulated Faces through Spatial Steganalysis and Temporal Features ICASSP 2020-2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) May 2020 Barcelona Spain IEEE 2952\u20132956.","DOI":"10.1109\/ICASSP40776.2020.9053969"},{"key":"e_1_2_12_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsidi.2021.301108"},{"key":"e_1_2_12_18_2","doi-asserted-by":"crossref","unstructured":"MarraF. GragnanielloD. VerdolivaL. andPoggiG. Do Gans Leave Artificial Fingerprints? 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) March 2019 San Jose CA IEEE 506\u2013511.","DOI":"10.1109\/MIPR.2019.00103"},{"key":"e_1_2_12_19_2","doi-asserted-by":"crossref","unstructured":"WesselkampV. RieckK. ArpD. andQuiringE. Misleading Deep-Fake Detection With Gan Fingerprints 2022 IEEE Security and Privacy Workshops (SPW) May 2022 59\u201365 https:\/\/doi.org\/10.1109\/spw54247.2022.9833860.","DOI":"10.1109\/SPW54247.2022.9833860"},{"key":"e_1_2_12_20_2","doi-asserted-by":"crossref","unstructured":"YuN. SkripniukV. AbdelnabiS. andFritzM. Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data Proceedings of the IEEE\/CVF International Conference on Computer Vision October 2021 Montreal QC 14 448\u2013514 457.","DOI":"10.1109\/ICCV48922.2021.01418"},{"key":"e_1_2_12_21_2","doi-asserted-by":"crossref","unstructured":"GuarneraL. GiudiceO. andBattiatoS. Deepfake Detection by Analyzing Convolutional Traces Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops June 2020 Seattle WA 666\u2013667.","DOI":"10.1109\/CVPRW50498.2020.00341"},{"key":"e_1_2_12_22_2","doi-asserted-by":"crossref","unstructured":"YuN. DavisL. S. andFritzM. Attributing Fake Images to Gans: Learning and Analyzing Gan Fingerprints Proceedings of the IEEE\/CVF International Conference on Computer Vision October 2019 Seoul Korea 7556\u20137566.","DOI":"10.1109\/ICCV.2019.00765"},{"key":"e_1_2_12_23_2","unstructured":"KimC. RenY. andYangY. Decentralized Attribution of Generative Models 9th International Conference on Learning Representations September 2021."},{"key":"e_1_2_12_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3301451"},{"key":"e_1_2_12_25_2","unstructured":"FinnC. AbbeelP. andLevineS. Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks International Conference on Machine Learning August 2017 Sydney Australia PMLR 1126\u20131135."},{"key":"e_1_2_12_26_2","article-title":"Probabilistic Model-Agnostic Meta-Learning","volume":"31","author":"Finn C.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3232290"},{"key":"e_1_2_12_28_2","doi-asserted-by":"crossref","unstructured":"HanB. LiJ. RenW. LuoM. LiuJ. andCaoX. Sigma-df: Single-Side Guided Meta-Learning for Deepfake Detection Proceedings of the 2023 ACM International Conference on Multimedia Retrieval June 2023 Thessaloniki Greece 153\u2013161 https:\/\/doi.org\/10.1145\/3591106.3592282.","DOI":"10.1145\/3591106.3592282"},{"key":"e_1_2_12_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3209336"},{"key":"e_1_2_12_30_2","unstructured":"AntoniouA. EdwardsH. andStorkeyA. How to Train Your Maml Seventh International Conference on Learning Representations November 2019."},{"key":"e_1_2_12_31_2","unstructured":"DeVriesT.andTaylorG. W. Improved Regularization of Convolutional Neural Networks with Cutout 2017."},{"key":"e_1_2_12_32_2","doi-asserted-by":"crossref","unstructured":"YunS. HanD. OhS. J. ChunS. ChoeJ. andYooY. Cutmix: Regularization Strategy to Train Strong Classifiers With Localizable Features Proceedings of the IEEE\/CVF International Conference on Computer Vision October 2019 Seoul Korea 6023\u20136032.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_2_12_33_2","unstructured":"ZhangH. Ciss\u00e9M. DauphinY. N. andLopez-PazD. Mixup: Beyond Empirical Risk Minimization 6th International Conference on Learning Representations April 2018."},{"key":"e_1_2_12_34_2","unstructured":"LimS. ErichsonN. UtreraF. XuW. andMahoneyM. Noisy Feature Mixup 10th International Conference on Learning Representations October 2022."},{"key":"e_1_2_12_35_2","unstructured":"YuN. SkripniukV. ChenD. DavisL. S. andFritzM. Responsible Disclosure of Generative Models Using Scalable Fingerprinting 10th International Conference on Learning Representations December 2022."},{"key":"e_1_2_12_36_2","doi-asserted-by":"crossref","unstructured":"JoslinM.andHaoS. Attributing and Detecting Fake Images Generated by Known Gans 2020 IEEE Security and Privacy Workshops (SPW) May 2020 San Francisco CA IEEE 8\u201314.","DOI":"10.1109\/SPW50608.2020.00019"},{"key":"e_1_2_12_37_2","unstructured":"XuanX. PengB. WangW. andDongJ. Scalable Fine-Grained Generated Image Classification Based on Deep Metric Learning 2019."},{"key":"e_1_2_12_38_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20391"},{"key":"e_1_2_12_39_2","unstructured":"NicholA. AchiamJ. andSchulmanJ. On First-Order Meta-Learning Algorithms 2018."},{"key":"e_1_2_12_40_2","article-title":"Bayesian Model-Agnostic Meta-Learning","volume":"31","author":"Yoon J.","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_41_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16367"},{"key":"e_1_2_12_42_2","first-page":"24 597","article-title":"Ost: Improving Generalization of Deepfake Detection via One-Shot Test-Time Training","volume":"35","author":"Chen L.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_43_2","unstructured":"JianS. KaimingH. ShaoqingR. andXiangyuZ. Deep Residual Learning for Image Recognition IEEE Conference on Computer Vision & Pattern Recognition June 2016 Las Vegas NV 770\u2013778."},{"key":"e_1_2_12_44_2","doi-asserted-by":"crossref","unstructured":"RonnebergerO. FischerP. andBroxT. U-Net: Convolutional Networks for Biomedical Image Segmentation Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference October 2015 Munich Germany Springer 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_12_45_2","unstructured":"MirzaM.andOsinderoS. Conditional Generative Adversarial Nets 2014."},{"key":"e_1_2_12_46_2","doi-asserted-by":"crossref","unstructured":"WooS. ParkJ. LeeJ.-Y. andKweonI. S. Cbam: Convolutional Block Attention Module Proceedings of the European Conference on Computer Vision (ECCV) September 2018 3\u201319 https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1 2-s2.0-85055111544.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_12_47_2","doi-asserted-by":"crossref","unstructured":"BuiT. YuN. andCollomosseJ. Repmix: Representation Mixing for Robust Attribution of Synthesized Images European Conference on Computer Vision October 2022 Springer 146\u2013163.","DOI":"10.1007\/978-3-031-19781-9_9"},{"key":"e_1_2_12_48_2","doi-asserted-by":"crossref","unstructured":"SelvarajuR. R. CogswellM. DasA. VedantamR. ParikhD. andBatraD. Grad-cam: Visual Explanations From Deep Networks via Gradient-Based Localization 2017 IEEE International Conference on Computer Vision (ICCV) October 2017 Venice Italy 618\u2013626.","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_12_49_2","article-title":"Imagenet Classification With Deep Convolutional Neural Networks","volume":"25","author":"Krizhevsky A.","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_12_50_2","unstructured":"SimonyanK.andZissermanA. Very Deep Convolutional Networks for Large-Scale Image Recognition 2014."}],"container-title":["International Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2024\/7950247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T16:05:17Z","timestamp":1730477117000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2024\/7950247"}},"subtitle":[],"editor":[{"given":"Stefano","family":"Cirillo","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["10.1155\/2024\/7950247"],"URL":"https:\/\/doi.org\/10.1155\/2024\/7950247","archive":["Portico"],"relation":{},"ISSN":["0884-8173","1098-111X"],"issn-type":[{"value":"0884-8173","type":"print"},{"value":"1098-111X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"2024-01-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-01","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"7950247"}}