{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T03:59:52Z","timestamp":1776398392042,"version":"3.51.2"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:00:00Z","timestamp":1747785600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Fake identities created using highly realistic synthetic face images have become increasingly prevalent in recent years, driven by advancements in generative neural networks that are readily accessible online and easy to use. These fake identities can be exploited for malicious purposes, such as spreading misinformation or committing fraud. Given the widespread availability of online content and the ease of generating fake online identities, it is desirable that users are able to distinguish real face images from synthetic ones. Additionally, it is important to explore whether specialized training can enhance the ability of individuals to detect synthetically generated face images. In this work, we address these challenges by designing an online experiment to evaluate human detection capabilities and the impact of training on detecting synthetic face images. As part of the experiments, we recruited 184 participants divided into an experimental group and a control group, where the experimental group underwent a tailored training session halfway through the experiment. The study shows that training may moderately enhance human capabilities to detect synthetic face images. Specifically, it was found that the experimental group generally outperformed the control group after training, primarily due to improved abilities in detecting synthetic face images. However, after training, the experimental group showed increased sensitivity and misclassified also more authentic face images, as compared to the control group.<\/jats:p>","DOI":"10.3389\/frai.2025.1568267","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T09:36:00Z","timestamp":1747820160000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Training humans for synthetic face image detection"],"prefix":"10.3389","volume":"8","author":[{"given":"Ramlah Sara","family":"Rehman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ewald","family":"Meier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mathias","family":"Ibsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christian","family":"Rathgeb","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Nichols","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Busch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,21]]},"reference":[{"key":"B1","unstructured":"Betker\n              J.\n            \n            \n              Goh\n              G.\n            \n            \n              Jing\n              L.\n            \n            \n              Brooks\n              T.\n            \n            \n              Wang\n              J.\n            \n            \n              Li\n              L.\n            \n          \n          Improving image generation with better captions\n          \n          2023"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2804","DOI":"10.1109\/CVPRW50498.2020.00337","article-title":"\u201cEvading deepfake-image detectors with white- and black-box attacks,\u201d","author":"Carlini","year":"2020","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jebo.2011.08.009","article-title":"Experimental methods: Between-subject and within-subject design","volume":"81","author":"Charness","year":"2012","journal-title":"J. Econ. Behav. Organ"},{"key":"B4","unstructured":"Regulation (eu) 2016\/679 (General Data Protection Regulation)\n          \n          2016"},{"key":"B5","doi-asserted-by":"publisher","first-page":"56","DOI":"10.54501\/jots.v1i4.56","article-title":"Creating, using, misusing, and detecting deep fakes","volume":"1","author":"Farid","year":"2022","journal-title":"J. Online Trust Safety"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1149","DOI":"10.3758\/BRM.41.4.1149","article-title":"Statistical power analyses using G*Power 3.1: tests for correlation and regression analyses","volume":"41","author":"Faul","year":"2009","journal-title":"Behav. Res. Methods"},{"key":"B7","doi-asserted-by":"publisher","first-page":"175","DOI":"10.3758\/BF03193146","article-title":"G*Power 3: a flexible statistical power analysis program for the social, behavioral, and biomedical sciences","volume":"39","author":"Faul","year":"2007","journal-title":"Behav. Res. Methods"},{"key":"B8","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1109\/MetroXRAINE58569.2023.10405682","article-title":"\u201cOn the human ability in detecting digitally manipulated face images,\u201d","author":"Franco","year":"2023","journal-title":"International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE)"},{"key":"B9","unstructured":"Freepik website\n          \n          2024"},{"key":"B10","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1109\/TTS.2022.3231450","article-title":"Analyzing human observer ability in morphing attack detection\u2013where do we stand?","volume":"4","author":"Godage","year":"2023","journal-title":"IEEE Trans. Technol. Soc"},{"key":"B11","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/978-3-030-87664-7_9","article-title":"\u201cDetection of AI-generated synthetic faces,\u201d","volume-title":"Handbook of Digital Face Manipulation and Detection: From DeepFakes to Morphing Attacks, Advances in Computer Vision and Pattern Recognition","author":"Gragnaniello","year":"2022"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2500","DOI":"10.1109\/ICASSP39728.2021.9414582","article-title":"\u201cExposing GAN-generated faces using inconsistent corneal specular highlights,\u201d","author":"Hu","year":"2021","journal-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"},{"key":"B13","doi-asserted-by":"publisher","first-page":"2729","DOI":"10.1109\/CVPRW50498.2020.00329","article-title":"\u201cDetecting CNN-generated facial images in real-world scenarios,\u201d","author":"Hulzebosch","year":"2020","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1109\/IWBF62628.2024.10593873","article-title":"\u201cMulti-channel cross modal detection of synthetic face images,\u201d","author":"Ibsen","year":"2024","journal-title":"IEEE International Workshop on Biometrics and Forensics (IWBF)."},{"key":"B15","doi-asserted-by":"publisher","first-page":"8107","DOI":"10.1109\/CVPR42600.2020.00813","article-title":"\u201cAnalyzing and improving the image quality of StyleGAN,\u201d","author":"Karras","year":"2020","journal-title":"Conference on Computer Vision and Pattern Recognition (CVPR), pages"},{"key":"B16","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1057\/s41304-024-00482-9","article-title":"On the way to deep fake democracy? Deep fakes in election campaigns in 2023","volume":"43","author":"\u0141abuz","year":"2024","journal-title":"Eur. Polit. Sci"},{"key":"B17","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1109\/MSP.2021.3120982","article-title":"More real than real: a study on human visual perception of synthetic faces","volume":"39","author":"Lago","year":"2022","journal-title":"IEEE Signal Process. Mag"},{"key":"B18","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1109\/WACVW.2019.00020","article-title":"\u201cExploiting visual artifacts to expose deepfakes and face manipulations,\u201d","author":"Matern","year":"2019","journal-title":"IEEE Winter Applications of Computer Vision Workshops (WACVW)"},{"key":"B19","first-page":"45","article-title":"Digital eye strain: prevention is the logical option","volume":"3","author":"Menaria","year":"2024","journal-title":"Intl. J. Nurs. Med. Invest"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1177\/09567976231207095","article-title":"AI hyperrealism: why AI faces are perceived as more real than human ones","volume":"34","author":"Miller","year":"2023","journal-title":"Psychol. Sci"},{"key":"B21","doi-asserted-by":"publisher","first-page":"884","DOI":"10.1109\/CVPRW59228.2023.00095","article-title":"\u201cExposing GAN-generated profile photos from compact embeddings,\u201d","author":"Mundra","year":"2023","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1109\/JSTSP.2020.3007250","article-title":"GANprintR: Improved fakes and evaluation of the state of the art in face manipulation detection","volume":"14","author":"Neves","year":"2020","journal-title":"IEEE J. Sel. Top. Signal Process"},{"key":"B23","doi-asserted-by":"publisher","first-page":"103525","DOI":"10.1016\/j.cviu.2022.103525","article-title":"Deep learning for deepfakes creation and detection: a survey","volume":"223","author":"Nguyen","year":"2022","journal-title":"Comput. Vision Image Understand"},{"key":"B24","doi-asserted-by":"publisher","first-page":"e2120481119","DOI":"10.1073\/pnas.2120481119","article-title":"AI-synthesized faces are indistinguishable from real faces and more trustworthy","volume":"119","author":"Nightingale","year":"2022","journal-title":"Proc. Natl. Acad. Sci"},{"key":"B25","unstructured":"Flickr-Faces-HQ Dataset (FFHQ)\n          \n          2019"},{"key":"B26","unstructured":"O'Sullivan\n              D.\n            \n          \n          A high school student created a fake 2020 candidate. Twitter verified it\n          \n          2020"},{"key":"B27","doi-asserted-by":"publisher","first-page":"4297","DOI":"10.1109\/CVPRW63382.2024.00433","article-title":"\u201cFinding AI-generated faces in the wild,\u201d","author":"Porcile","year":"2024","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2200","DOI":"10.1109\/ICIP49359.2023.10222083","article-title":"\u201cArtifact: a large-scale dataset with artificial and factual images for generalizable and robust synthetic image detection,\u201d","author":"Rahman","year":"2023","journal-title":"IEEE International Conference on Image Processing (ICIP), pages"},{"key":"B29","article-title":"\u201cHandbook of digital face manipulation and detection: from deepfakes to morphing attacks,\u201d","volume-title":"Advances in Computer Vision and Pattern Recognition","author":"Rathgeb","year":"2022"},{"key":"B30","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1177\/0098628316677643","article-title":"Psytoolkit: A novel web-based method for running online questionnaires and reaction-time experiments","volume":"44","author":"Stoet","year":"2016","journal-title":"Teach. Psychol"},{"key":"B31","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1007\/978-3-030-87664-7_21","article-title":"\u201cFuture trends in digital face manipulation and detection,\u201d","volume-title":"Handbook of Digital Face Manipulation and Detection: From DeepFakes to Morphing Attacks, Advances in Computer Vision and Pattern Recognition","author":"Tolosana","year":"2022"},{"key":"B32","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.inffus.2020.06.014","article-title":"Deepfakes and beyond: a survey of face manipulation and fake detection","volume":"64","author":"Tolosana","year":"2020","journal-title":"Inf. Fusion"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1288","DOI":"10.1037\/xlm0000972","article-title":"Diagnostic feature training improves face matching accuracy","volume":"47","author":"Towler","year":"2021","journal-title":"J. Exper. Psychol"},{"key":"B34","unstructured":"Ulmer\n              A.\n            \n            \n              Tong\n              A.\n            \n          \n          Deepfaking it: America's 2024 election collides with AI boom\n          \n          2023"},{"key":"B35","doi-asserted-by":"publisher","first-page":"8692","DOI":"10.1109\/CVPR42600.2020.00872","article-title":"\u201cCNN-generated images are surprisingly easy to spot\u2026for now,\u201d","author":"Wang","year":"2020","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B36","doi-asserted-by":"publisher","first-page":"129494","DOI":"10.1109\/ACCESS.2019.2939812","article-title":"No one can escape: a general approach to detect tampered and generated image","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"B37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/WIFS47025.2019.9035107","article-title":"\u201cDetecting and simulating artifacts in GAN fake images,\u201d","author":"Zhang","year":"2019","journal-title":"IEEE Internationl Workshop on Information Forensics and Security (WIFS)"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1568267\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T09:36:06Z","timestamp":1747820166000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1568267\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,21]]},"references-count":37,"alternative-id":["10.3389\/frai.2025.1568267"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1568267","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,21]]},"article-number":"1568267"}}