mlsanityData to 14 Oct 2026

Face Morphing Attacks and Face Image Quality: The Effect of Morphing and the Unsupervised Attack Detection by Quality

arXiv 2208.05864 ↗First posted 11 Aug 2022cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Morphing attacks are a form of presentation attacks that gathered increasing attention in recent years. A morphed image can be successfully verified to multiple identities. This operation, therefore, poses serious security issues related to the ability of a travel or identity document to be verified to belong to multiple persons. Previous works touched on the issue of the quality of morphing attack images, however, with the main goal of quantitatively proofing the realistic appearance of the produced morphing attacks. We theorize that the morphing processes might have an effect on both, the perceptual image quality and the image utility in face recognition (FR) when compared to bona fide samples. Towards investigating this theory, this work provides an extensive analysis of the effect of morphing on face image quality, including both general image quality measures and face image utility measures. This analysis is not limited to a single morphing technique, but rather looks at six different morphing techniques and five different data sources using ten different quality measures. This analysis reveals consistent separability between the quality scores of morphing attack and bona fide samples measured by certain quality measures. Our study goes further to build on this effect and investigate the possibility of performing unsupervised morphing attack detection (MAD) based on quality scores. Our study looks intointra and inter-dataset detectability to evaluate the generalizability of such a detection concept on different morphing techniques and bona fide sources. Our final results point out that a set of quality measures, such as MagFace and CNNNIQA, can be used to perform unsupervised and generalized MAD with a correct classification accuracy of over 70%.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 34 of its 85 references that are in the map. First posted on arXiv 11 Aug 2022.

Builds on

34 of 85 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  4. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  5. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  6. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 903
  7. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 334
  8. 2019Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Networkcited by 302
  9. 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 225
  10. 2017RankIQA: Learning from Rankings for No-reference Image Quality Assessmentcited by 151
  11. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 144
  12. 2020Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wildcited by 134
22 more
  1. 2020SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustnesscited by 112
  2. 2019dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairscited by 73
  3. 2021CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiabilitycited by 69
  4. 2020Face Morphing Attack Generation & Detection: A Comprehensive Surveycited by 64
  5. 2021SDD-FIQA: Unsupervised Face Image Quality Assessment with Similarity Distribution Distancecited by 64
  6. 2019FaceQnet: Quality Assessment for Face Recognition based on Deep Learningcited by 62
  7. 2022Privacy-friendly Synthetic Data for the Development of Face Morphing Attack Detectorscited by 47
  8. 2020Deep Face Representations for Differential Morphing Attack Detectioncited by 46
  9. 2020Can GAN Generated Morphs Threaten Face Recognition Systems Equally as Landmark Based Morphs? -- Vulnerability and Detectioncited by 46
  10. 2020Vulnerability Analysis of Face Morphing Attacks from Landmarks and Generative Adversarial Networkscited by 36
  11. 2021MixFaceNets: Extremely Efficient Face Recognition Networkscited by 36
  12. 2021PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillationcited by 36
  13. 2020Face Quality Estimation and Its Correlation to Demographic and Non-Demographic Bias in Face Recognitioncited by 31
  14. 2021PW-MAD: Pixel-wise Supervision for Generalized Face Morphing Attack Detectioncited by 29
  15. 2019Face morphing detection in the presence of printing/scanning and heterogeneous image sourcescited by 22
  16. 2021ReGenMorph: Visibly Realistic GAN Generated Face Morphing Attacks by Attack Re-generationcited by 21
  17. 2021Real Masks and Spoof Faces: On the Masked Face Presentation Attack Detectioncited by 20
  18. 2021A Deep Insight into Measuring Face Image Utility with General and Face-specific Image Quality Metricscited by 13
  19. 2020Differential Morphed Face Detection Using Deep Siamese Networkscited by 12
  20. 2021Detection of Morphed Face Images Using Discriminative Wavelet Sub-bandscited by 10
  21. 2021The Effect of Wearing a Face Mask on Face Image Qualitycited by 7
  22. 2021Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Modelscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 3; 2026: 1.

8 papers.

  1. 2023MorDIFF: Recognition Vulnerability and Attack Detectability of Face Morphing Attacks Created by Diffusion Autoencoderscited by 44
  2. 2025SelfMAD: Enhancing Generalization and Robustness in Morphing Attack Detection via Self-Supervised Learningcited by 7
  3. 2025StableMorph: High-Quality Face Morph Generation with Stable Diffusioncited by 2
  4. 2024V-MAD: Video-based Morphing Attack Detection in Operational Scenarioscited by 1
  5. 2024Fusion is all you need: Face Fusion for Customized Identity-Preserving Image Synthesiscited by 1
  6. 2026Emergent Morphing Attack Detection in Open Multi-modal Large Language Modelscited by 1
  7. 2023Towards Generalizable Morph Attack Detection with Consistency Regularizationcited by 0
  8. 2025Radial Distortion in Face Images: Detection and Impactcited by 0