{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T10:58:32Z","timestamp":1762253912634,"version":"build-2065373602"},"reference-count":50,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,9,18]],"date-time":"2021-09-18T00:00:00Z","timestamp":1631923200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Horizon 2020","award":["833704"],"award-info":[{"award-number":["833704"]}]},{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["13N15735"],"award-info":[{"award-number":["13N15735"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Detecting morphed face images has become an important task to maintain the trust in automated verification systems based on facial images, e.g., at automated border control gates. Deep Neural Network (DNN)-based detectors have shown remarkable results, but without further investigations their decision-making process is not transparent. In contrast to approaches based on hand-crafted features, DNNs have to be analyzed in complex experiments to know which characteristics or structures are generally used to distinguish between morphed and genuine face images or considered for an individual morphed face image. In this paper, we present Feature Focus, a new transparent face morphing detector based on a modified VGG-A architecture and an additional feature shaping loss function, as well as Focused Layer-wise Relevance Propagation (FLRP), an extension of LRP. FLRP in combination with the Feature Focus detector forms a reliable and accurate explainability component. We study the advantages of the new detector compared to other DNN-based approaches and evaluate LRP and FLRP regarding their suitability for highlighting traces of image manipulation from face morphing. To this end, we use partial morphs which contain morphing artifacts in predefined areas only and analyze how much of the overall relevance each method assigns to these areas.<\/jats:p>","DOI":"10.3390\/computers10090117","type":"journal-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T07:52:14Z","timestamp":1632124334000},"page":"117","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Feature Focus: Towards Explainable and Transparent Deep Face Morphing Attack Detectors"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-5934","authenticated-orcid":false,"given":"Clemens","family":"Seibold","sequence":"first","affiliation":[{"name":"Department of Vision and Imaging Technologies, Fraunhofer Heinrich-Hertz-Institute, 10587 Berlin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2086-0951","authenticated-orcid":false,"given":"Anna","family":"Hilsmann","sequence":"additional","affiliation":[{"name":"Department of Vision and Imaging Technologies, Fraunhofer Heinrich-Hertz-Institute, 10587 Berlin, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8378-4805","authenticated-orcid":false,"given":"Peter","family":"Eisert","sequence":"additional","affiliation":[{"name":"Department of Vision and Imaging Technologies, Fraunhofer Heinrich-Hertz-Institute, 10587 Berlin, Germany"},{"name":"Department of Visual Computing, Humboldt Universit\u00e4t zu Berlin, 10117 Berlin, Germany"}]}],"member":"1968","published-online":{"date-parts":[[2021,9,18]]},"reference":[{"key":"ref_1","unstructured":"Ferrara, M., Franco, A., and Maltoni, D. (October, January 29). The magic passport. Proceedings of the IEEE International Joint Conference on Biometrics, Clearwater, FL, USA."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ferrara, M., Franco, A., and Maltoni, D. (2016). On the Effects of Image Alterations on Face Recognition Accuracy. Face Recognition across the Imaging Spectrum, Springer.","DOI":"10.1007\/978-3-319-28501-6_9"},{"key":"ref_3","unstructured":"Lewis, M., and Statham, P. (2004, January 20\u201322). CESG Biometric Security Capabilities Programme: Method, Results and Research challenges. Proceedings of the Biometrics Consortium Conference (BCC), Arlington, VA, USA."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"23012","DOI":"10.1109\/ACCESS.2019.2899367","article-title":"Face Recognition Systems Under Morphing Attacks: A Survey","volume":"7","author":"Scherhag","year":"2019","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Makrushin, A., and Wolf, A. (2018, January 3\u20137). An Overview of Recent Advances in Assessing and Mitigating the Face Morphing Attack. Proceedings of the EUSIPCO 2018: 26th European Signal Processing Conference, Roma, Italy.","DOI":"10.23919\/EUSIPCO.2018.8553599"},{"key":"ref_6","first-page":"2","article-title":"Developing harmonized automated border control (ABS) training capabilities","volume":"12","year":"2017","journal-title":"ICAO TRIP Mag."},{"key":"ref_7","unstructured":"European Commission (2016). Action Plan to Strengthen the European Response to Travel Document Fraud, Council of the European Union."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ngan, M., Grother, P., Hanaoka, K., and Kuo, J. (2020). Face Recognition Vendor Test (FRVT) Part 4: MORPH\u2014Performance of Automated Face Morph Detection, NIST Interagency\/Internal Report (NISTIR).","DOI":"10.6028\/NIST.IR.8292"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Adjabi, I., Ouahabi, A., Benzaoui, A., and Taleb-Ahmed, A. (2020). Past, Present, and Future of Face Recognition: A Review. Electronics, 9.","DOI":"10.20944\/preprints202007.0479.v1"},{"key":"ref_10","unstructured":"Minaee, S., Luo, P., Lin, Z.L., and Bowyer, K. (2021). Going Deeper Into Face Detection: A Survey. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Seibold, C., Samek, W., Hilsmann, A., and Eisert, P. (2017, January 23\u201325). Detection of Face Morphing Attacks by Deep Learning. Proceedings of the 16th International Workshop, IWDW 2017, Magdeburg, Germany.","DOI":"10.1007\/978-3-319-64185-0_9"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Debiasi, L., Rathgeb, C., Scherhag, U., Uhl, A., and Busch, C. (2018, January 22\u201325). PRNU Variance Analysis for Morphed Face Image Detection. Proceedings of the 9th IEEE International Conference on Biometrics Theory, Applications and Systems, Redondo Beach, CA, USA.","DOI":"10.1109\/BTAS.2018.8698576"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1109\/TBIOM.2019.2942395","article-title":"Detection of Face Morphing Attacks Based on PRNU Analysis","volume":"1","author":"Scherhag","year":"2019","journal-title":"IEEE Trans. Biom. Behav. Identity Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1038\/s41467-019-08987-4","article-title":"Unmasking Clever Hans Predictors and Assessing What Machines Really Learn","volume":"10","author":"Lapuschkin","year":"2019","journal-title":"Nat. Commun."},{"key":"ref_15","first-page":"102526","article-title":"Accurate and robust neural networks for face morphing attack detection","volume":"53","author":"Seibold","year":"2020","journal-title":"J. Inf. Secur. Appl."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Seibold, C., Hilsmann, A., and Eisert, P. (2021, January 5\u20139). Focused LRP: Explainable AI for Face Morphing Attack Detection. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, Waikola, HI, USA.","DOI":"10.1109\/WACVW52041.2021.00014"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bach, S., Binder, A., Montavon, G., Klauschen, F., M\u00fcller, K.R., and Samek, W. (2015). On Pixel-wise Explanations for Non-Linear Classifier Decisions by Layer-wise Relevance Propagation. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref_18","unstructured":"Seibold, C., Hilsmann, A., and Eisert, P. (2019, January 18\u201320). Style Your Face Morph and Improve Your Face Morphing Attack Detector. Proceedings of the International Conference of the Biometrics Special Interest Group, Darmstadt, Germany."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3625","DOI":"10.1109\/TIFS.2020.2994750","article-title":"Deep Face Representations for Differential Morphing Attack Detection","volume":"15","author":"Scherhag","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Banerjee, S., and Ross, A. (2021, January 4\u20137). Conditional Identity Disentanglement for Differential Face Morph Detection. Proceedings of the 2021 IEEE International Joint Conference on Biometrics (IJCB), Shenzhen, China.","DOI":"10.1109\/IJCB52358.2021.9484355"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1008","DOI":"10.1109\/TIFS.2017.2777340","article-title":"Face Demorphing","volume":"13","author":"Ferrara","year":"2018","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"75122","DOI":"10.1109\/ACCESS.2019.2920713","article-title":"FD-GAN: Face De-Morphing Generative Adversarial Network for Restoring Accomplice\u2019s Facial Image","volume":"7","author":"Peng","year":"2019","journal-title":"IEEE Access"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Seibold, C., Hilsmann, A., and Eisert, P. (2018, January 3\u20137). Reflection Analysis for Face Morphing Attack Detection. Proceedings of the 26th European Signal Processing Conference (EUSIPCO), Roma, Italy.","DOI":"10.23919\/EUSIPCO.2018.8553116"},{"key":"ref_24","unstructured":"Makrushin, A., Neubert, T., and Dittmann, J. (March, January 27). Automatic Generation and Detection of Visually Faultless Facial Morphs. Proceedings of the VISIGRAPP\u2014Volume 6: VISAPP, Porto, Portugal."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Neubert, T. (2017, January 23\u201325). Face Morphing Detection: An Approach Based on Image Degradation Analysis. Proceedings of the 16th International Workshop on Digital-forensics and Watermarking (IWDW 2017), Magdeburg, Germany.","DOI":"10.1007\/978-3-319-64185-0_8"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Neubert, T., Kraetzer, C., and Dittmann, J. (2019, January 3\u20135). A Face Morphing Detection Concept with a Frequency and a Spatial Domain Feature Space for Images on eMRTD. Proceedings of the ACM Workshop on Information Hiding and Multimedia Security, Paris, France.","DOI":"10.1145\/3335203.3335721"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ramachandra, R., Raja, K.B., and Busch, C. (2016, January 6\u20139). Detecting morphed face images. Proceedings of the 8th IEEE International Conference on Biometrics Theory, Applications and Systems, Niagara Falls, NY, USA.","DOI":"10.1109\/BTAS.2016.7791169"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Damer, N., Zienert, S., Wainakh, Y., Saladi\u00e9, A.M., Kirchbuchner, F., and Kuijper, A. (2019, January 2\u20135). A Multi-detector Solution Towards an Accurate and Generalized Detection of Face Morphing Attacks. Proceedings of the 2019 22th International Conference on Information Fusion (FUSION), Ottawa, ON, Canada.","DOI":"10.23919\/FUSION43075.2019.9011378"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Makrushin, A., Kraetzer, C., Dittmann, J., Seibold, C., Hilsmann, A., and Eisert, P. (2019, January 2\u20136). Dempster-Shafer Theory for Fusing Face Morphing Detectors. Proceedings of the 2019 27th European Signal Processing Conference (EUSIPCO), A Coruna, Spain.","DOI":"10.23919\/EUSIPCO.2019.8902533"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., and Fergus, R. (2014, January 6\u201312). Visualizing and Understanding Convolutional Networks. Proceedings of the ECCV 2014: 13th European Conference, Zurich, Switzerland.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref_31","unstructured":"Chen, C., Li, O., Barnett, A., Su, J., and Rudin, C. (2018). This looks like that: Deep learning for interpretable image recognition. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the ICCV IEEE Computer Society, Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kohlbrenner, M., Bauer, A., Nakajima, S., Binder, A., Samek, W., and Lapuschkin, S. (2020, January 19\u201324). Towards best practice in explaining neural network decisions with LRP. Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), Glasgow, UK.","DOI":"10.1109\/IJCNN48605.2020.9206975"},{"key":"ref_34","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.patrec.2021.01.010","article-title":"Deep learning for real-time semantic segmentation: Application in ultrasound imaging","volume":"144","author":"Ouahabi","year":"2021","journal-title":"Pattern Recognit. Lett."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Yin, L., Chen, X., Sun, Y., Worm, T., and Reale, M. (2008, January 17\u201319). A high-resolution 3D dynamic facial expression database. Proceedings of the 8th IEEE International Conference on Automatic Face Gesture Recognition, Amsterdam, The Netherland.","DOI":"10.1109\/AFGR.2008.4813324"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.3758\/s13428-014-0532-5","article-title":"The Chicago face database: A free stimulus set of faces and norming data","volume":"47","author":"Ma","year":"2015","journal-title":"Behav. Res. Methods"},{"key":"ref_38","unstructured":"Phillips, P.J. (2003). Color FERET Database."},{"key":"ref_39","unstructured":"DeBruine, L., and Jones, B. (2017). Face Research Lab London Set. figshare."},{"key":"ref_40","first-page":"59","article-title":"The PUT face database","volume":"13","author":"Florek","year":"2008","journal-title":"Image Process. Commun."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1007\/s11042-009-0417-2","article-title":"SCface\u2014Surveillance Cameras Face Database","volume":"51","author":"Grgic","year":"2011","journal-title":"Multimed. Tools Appl."},{"key":"ref_42","unstructured":"Hancock, P. (2008). Utrecht ECVP Face Dataset, School of Natural Sciences, University of Stirling. Available online: http:\/\/pics.stir.ac.uk\/."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017, January 21\u201326). Xception: Deep Learning with Depthwise Separable Convolutions. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Malolan, B., Parekh, A., and Kazi, F. (2020, January 9\u201312). Explainable Deep-Fake Detection Using Visual Interpretability Methods. Proceedings of the 2020 3rd International Conference on Information and Computer Technologies (ICICT), San Jose, CA, USA.","DOI":"10.1109\/ICICT50521.2020.00051"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1145\/882262.882269","article-title":"Poisson Image Editing","volume":"22","author":"Gangnet","year":"2003","journal-title":"ACM Trans. Graph."},{"key":"ref_46","unstructured":"(2021, July 20). Fraunhofer HHI and TU Berlin. Available online: http:\/\/heatmapping.org."},{"key":"ref_47","unstructured":"Lapuschkin, S. (2019). Opening the Machine Learning Black Box with Layer-Wise Relevance Propagation. [Ph.D. Thesis, Technische Universit\u00e4t Berlin]."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Jiang, P.T., Zhang, C.B., Hou, Q., Cheng, M.M., and Wei, Y. (2021). LayerCAM: Exploring Hierarchical Class Activation Maps. IEEE Trans. Image Process.","DOI":"10.1109\/TIP.2021.3089943"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Seibold, C., Hilsmann, A., Makrushin, A., Kraetzer, C., Neubert, T., Dittmann, J., and Eisert, P. (2019, January 9\u201312). Visual Feature Space Analyses of Face Morphing Detectors. Proceedings of the 2019 IEEE International Workshop on Information Forensics and Security (WIFS), Delft, The Netherlands.","DOI":"10.1109\/WIFS47025.2019.9034983"},{"key":"ref_50","unstructured":"International Organization for Standardization (2017). Information Technology\u2014Biometric Presentation Attack Detection\u2014Part 3: Testing and Reporting, International Organization for Standardization. Available online: https:\/\/www.iso.org\/standard\/67381.html."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/10\/9\/117\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:01:49Z","timestamp":1760166109000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/10\/9\/117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,18]]},"references-count":50,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["computers10090117"],"URL":"https:\/\/doi.org\/10.3390\/computers10090117","relation":{},"ISSN":["2073-431X"],"issn-type":[{"type":"electronic","value":"2073-431X"}],"subject":[],"published":{"date-parts":[[2021,9,18]]}}}