{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:10:12Z","timestamp":1778001012717,"version":"3.51.4"},"reference-count":36,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T00:00:00Z","timestamp":1745971200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006754","name":"DEVCOM ARL Army Research Office","doi-asserted-by":"publisher","award":["W911NF-21-1-0326"],"award-info":[{"award-number":["W911NF-21-1-0326"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Currently, the phenomenon of deepfakes is becoming increasingly significant, as they enable the creation of extremely realistic images capable of deceiving anyone thanks to deep learning tools based on generative adversarial networks (GANs). These images are used as profile pictures on social media with the intent to sow discord and perpetrate scams on a global scale. In this study, we demonstrate that these images can be identified through various imperfections present in the synthesized eyes, such as the irregular shape of the pupil and the difference between the corneal reflections of the two eyes. These defects result from the absence of physical and physiological constraints in most GAN models. We develop a two-level architecture capable of detecting these fake images. This approach begins with an automatic segmentation method for the pupils to verify their shape, as real image pupils naturally have a regular shape, typically round. Next, for all images where the pupils are not regular, the entire image is analyzed to verify the reflections. This step involves passing the facial image through an architecture that extracts and compares the specular reflections of the corneas of the two eyes, assuming that the eyes of real people observing a light source should reflect the same thing. Our experiments with a large dataset of real images from the Flickr-FacesHQ and CelebA datasets, as well as fake images from StyleGAN2 and ProGAN, show the effectiveness of our method. Our experimental results on the Flickr-Faces-HQ (FFHQ) dataset and images generated by StyleGAN2 demonstrated that our algorithm achieved a remarkable detection accuracy of 0.968 and a sensitivity of 0.911. Additionally, the method had a specificity of 0.907 and a precision of 0.90 for this same dataset. And our experimental results on the CelebA dataset and images generated by ProGAN also demonstrated that our algorithm achieved a detection accuracy of 0.870 and a sensitivity of 0.901. Moreover, the method had a specificity of 0.807 and a precision of 0.88 for this same dataset. Our approach maintains good stability of physiological properties during deep learning, making it as robust as some single-class deepfake detection methods. The results of the tests on the selected datasets demonstrate higher accuracy compared to other methods.<\/jats:p>","DOI":"10.3390\/info16050371","type":"journal-article","created":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T09:16:12Z","timestamp":1746090972000},"page":"371","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["The Eyes: A Source of Information for Detecting Deepfakes"],"prefix":"10.3390","volume":"16","author":[{"given":"Elisabeth","family":"Tchaptchet","sequence":"first","affiliation":[{"name":"Mathematics and Computer Science Department, University of Dschang, Dschang P.O. Box 96, Cameroon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elie Fute","family":"Tagne","sequence":"additional","affiliation":[{"name":"Mathematics and Computer Science Department, University of Buea, Buea P.O. Box 63, Cameroon"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaime","family":"Acosta","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory, Network Security Branch, Adelphi, MD 21005, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3638-3464","authenticated-orcid":false,"given":"Danda B.","family":"Rawat","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Howard University, Washington, DC 20059, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles","family":"Kamhoua","sequence":"additional","affiliation":[{"name":"DEVCOM Army Research Laboratory, Network Security Branch, Adelphi, MD 21005, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,30]]},"reference":[{"key":"ref_1","first-page":"2672","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2020, January 13\u201319). Analyzing and improving the image quality of stylegan. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref_3","unstructured":"Karras, T., Aila, T., Laine, S., and Lehtinen, J. (May, January 30). Progressive growing of GANs for improved quality, stability, and variation. Proceedings of the International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Guo, H., Hu, S., Wang, X., Chang, M.-C., and Lyu, S. (2022, January 22\u201327). Eyes tell all: Irregular pupil shapes reveal gan-generated faces. Proceedings of the ICASSP 2022\u20142022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore.","DOI":"10.1109\/ICASSP43922.2022.9746597"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hu, S., Li, Y., and Lyu, S. (2021, January 6\u201311). Exposing gan-generated faces using inconsistent corneal specular highlights. Proceedings of the ICASSP 2021\u20142021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9414582"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Tchaptchet, E., Tagne, E.F., Acosta, J., Danda, R., and Kamhoua, C. (2024, January 19\u201322). Detecting Deepfakes Using GAN Manipulation Defects in Human Eyes. Proceedings of the 2024 International Conference on Computing, Networking and Communications (ICNC), Big Island, HI, USA.","DOI":"10.1109\/ICNC59896.2024.10556045"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Marra, F., Gragnaniello, D., Verdoliva, L., and Poggi, G. (2019, January 28\u201330). Do gans leave artificial fingerprints?. Proceedings of the 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), San Jose, CA, USA.","DOI":"10.1109\/MIPR.2019.00103"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wang, S.-Y., Wang, O., Zhang, R., Owens, A., and Efros, A.A. (2020, January 13\u201319). Cnngenerated images are surprisingly easy to spot... for now. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Matern, F., Riess, C., and Stamminger, M. (2019, January 7\u201311). Exploiting visual artifacts to expose deepfakes and face manipulations. Proceedings of the 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW), Waikoloa Village, HI, USA.","DOI":"10.1109\/WACVW.2019.00020"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6111","DOI":"10.1109\/TPAMI.2021.3093446","article-title":"Deepfake detection based on discrepancies between faces and their context","volume":"44","author":"Nirkin","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wang, J., Wu, Z., Ouyang, W., Han, X., Chen, J., Jiang, Y.-G., and Li, S.-N. (June, January 27\u2013). M2tr: Multi-modal multi-scale transformers for deepfake detection. Proceedings of the 2022 International Conference on Multimedia Retrieval, Newark, NJ, USA.","DOI":"10.1145\/3512527.3531415"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., and Aila, T. (2019, January 15\u201320). A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Yang, X., Li, Y., Qi, H., and Lyu, S. (2019, January 3\u20135). Exposing gan-synthesized faces using landmark locations. Proceedings of the ACM Workshop on Information Hiding and Multimedia Security (IHMMSec), Paris, France.","DOI":"10.1145\/3335203.3335724"},{"key":"ref_14","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":"ref_15","unstructured":"Verdoliva, D.C.G.P.L. (2019, January 15\u201320). Extracting camera-based fingerprints for video forensics. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, Long Beach, CA, USA."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Cozzolino, D., and Verdoliva, L. (2018, January 3\u20137). Camera-based Image Forgery Localization using Convolutional Neural Networks. Proceedings of the 2018 26th European Signal Processing Conference (EUSIPCO), Rome, Italy.","DOI":"10.23919\/EUSIPCO.2018.8553581"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, L., Bao, J., Zhang, T., Yang, H., Chen, D., Wen, F., and Guo, B. (2020, January 13\u201319). Face X-ray for more general face forgery detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ciftci, U.A., Demir, I., and Yin, L. (2021). Fakecatcher: Detection of synthetic portrait videos using biological signals. IEEE Trans. Pattern Anal. Mach. Intell., 1.","DOI":"10.1109\/TPAMI.2020.3009287"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Agarwal, S., Farid, H., El-Gaaly, T., and Lim, S.N. (2020, January 6\u201311). Detecting deep-fake videos from appearance and behavior. Proceedings of the 2020 IEEE International Workshop on Information Forensics and Security (WIFS), New York, NY, USA.","DOI":"10.1109\/WIFS49906.2020.9360904"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3673","DOI":"10.1109\/TCSVT.2021.3106047","article-title":"A Unified Framework for High Fidelity Face Swap and Expression Reenactment","volume":"32","author":"Peng","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., and Manocha, D. (2020, January 12\u201316). Emotions don\u2019t lie: An audio-visual deepfake detection method using affective cues. Proceedings of the 28th ACM International Conference on Multimedia, Seattle, WA, USA.","DOI":"10.1145\/3394171.3413570"},{"key":"ref_22","unstructured":"Zhang, Y., Goh, J., Win, L.L., and Thing, V.L. (2016, January 14\u201315). Image Region Forgery Detection: A Deep Learning Approach. Proceedings of the Singapore Cyber-Security Conference (SG-CRC), Singapore."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.jvcir.2018.01.010","article-title":"Image splicing localization using a multi-task fully convolutional network (MFCN)","volume":"51","author":"Salloum","year":"2018","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Cheng, B., Girshick, R., Doll\u00b4ar, P., Berg, A.C., and Kirillov, A. (2021, January 20\u201325). Boundary iou: Improving object-centric image segmentation evaluation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Xue, Z., Jiang, X., Liu, Q., and Wei, Z. (2023). Global\u2013local facial fusion based gan generated fake face detection. Sensors, 23.","DOI":"10.3390\/s23020616"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"He, Y., Yu, N., Keuper, M., and Fritz, M. (2021). Beyond the spectrum: Detecting deepfakes via re-synthesis. arXiv.","DOI":"10.24963\/ijcai.2021\/349"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhang, Y., Yan, J., and Liu, W. (2021, January 20\u201325). Generalizing face forgery detection with high-frequency features. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"ref_28","unstructured":"Brock, A., Donahue, J., and Simonyan, K. (2018). Large scale gan training for high fidelity natural image synthesis. arXiv."},{"key":"ref_29","unstructured":"Arjovsky, M., Chintala, S., and Bottou, L. (2017, January 6\u201311). Wasserstein generative adversarial networks. Proceedings of the International Conference on Machine Learning, Sydney, Australia."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Bulat, A., Yang, J., and Tzimiropoulos, G. (2018, January 8\u201314). To learn image super-resolution, use a gan to learn how to do image degradation first. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01231-1_12"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1007\/s11831-019-09388-y","article-title":"Applications of generative adversarial networks (gans): An updated review","volume":"28","author":"Alqahtani","year":"2021","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_32","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"King","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref_33","unstructured":"Wang, C., Wang, Y., Zhang, K., Muhammad, J., Lu, T., Zhang, Q., Tian, Q., He, Z., Sun, Z., and Zhang, Y. (2021, January 4\u20137). Nir iris challenge evaluation in non-cooperative environments: Segmentation and localization. Proceedings of the 2021 IEEE International Joint Conference on Biometrics (IJCB), Shenzhen, China."},{"key":"ref_34","unstructured":"Tan, M., and Le, Q. (2019, January 10\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1109\/83.366472","article-title":"A new criterion for automatic multilevel thresholding","volume":"4","author":"Yen","year":"1995","journal-title":"IEEE Trans. Image Process."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., and Tang, X. (2015, January 7\u201313). Deep learning face attributes in the wild. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.425"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/5\/371\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:25:33Z","timestamp":1760030733000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/5\/371"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,30]]},"references-count":36,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["info16050371"],"URL":"https:\/\/doi.org\/10.3390\/info16050371","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,30]]}}}