mlsanityData to 13 Oct 2026

Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs

arXiv 2404.06025 ↗First posted 9 Apr 2024cs.CV cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Morphing attacks are an emerging threat to state-of-the-art Face Recognition (FR) systems, which aim to create a single image that contains the biometric information of multiple identities. Diffusion Morphs (DiM) are a recently proposed morphing attack that has achieved state-of-the-art performance for representation-based morphing attacks. However, none of the existing research on DiMs have leveraged the iterative nature of DiMs and left the DiM model as a black box, treating it no differently than one would a Generative Adversarial Network (GAN) or Varational AutoEncoder (VAE). We propose a greedy strategy on the iterative sampling process of DiM models which searches for an optimal step guided by an identity-based heuristic function. We compare our proposed algorithm against ten other state-of-the-art morphing algorithms using the open-source SYN-MAD 2022 competition dataset. We find that our proposed algorithm is unreasonably effective, fooling all of the tested FR systems with an MMPMR of 100%, outperforming all other morphing algorithms compared.

Key facts. Cited by 10 papers in the map (data through 13 Oct 2026). Builds on 31 of its 60 references that are in the map. First posted on arXiv 9 Apr 2024.

Builds on

31 of 60 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,093
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,321
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,082
  4. 2020Denoising Diffusion Implicit Modelscited by 9,718
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,028
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,213
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,000
  8. 2017Squeeze-and-Excitation Networkscited by 4,772
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,023
  10. 2021Alias-Free Generative Adversarial Networkscited by 1,183
  11. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 931
  12. 2016Universal adversarial perturbationscited by 782
19 more
  1. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 769
  2. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 448
  3. 2022AdaFace: Quality Adaptive Margin for Face Recognitioncited by 391
  4. 2020Partial FC: Training 10 Million Identities on a Single Machinecited by 163
  5. 2021ElasticFace: Elastic Margin Loss for Deep Face Recognitioncited by 144
  6. 2020Face Morphing Attack Generation & Detection: A Comprehensive Surveycited by 64
  7. 2020Improved Residual Networks for Image and Video Recognitioncited by 52
  8. 2020Can GAN Generated Morphs Threaten Face Recognition Systems Equally as Landmark Based Morphs? -- Vulnerability and Detectioncited by 46
  9. 2020Morphing Attack Detection -- Database, Evaluation Platform and Benchmarkingcited by 38
  10. 2022Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesiscited by 31
  11. 2022SYN-MAD 2022: Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Datacited by 30
  12. 2022Are GAN-based Morphs Threatening Face Recognition?cited by 28
  13. 2023How to Scale Your EMAcited by 22
  14. 2022Morphing Attack Potentialcited by 15
  15. 2023Leveraging Diffusion For Strong and High Quality Face Morphing Attackscited by 14
  16. 2022On the detection of morphing attacks generated by GANscited by 9
  17. 2023Fast-DiM: Towards Fast Diffusion Morphscited by 6
  18. 2021Adversarially Perturbed Wavelet-based Morphed Face Generationcited by 4
  19. 2023Worst-Case Morphs using Wasserstein ALI and Improved MIPGANcited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 5; 2026: 4.

10 papers.

  1. 2024AdjointDEIS: Efficient Gradients for Diffusion Modelscited by 7
  2. 2025SelfMAD: Enhancing Generalization and Robustness in Morphing Attack Detection via Self-Supervised Learningcited by 7
  3. 2026FD-MAD: Frequency-Domain Residual Analysis for Face Morphing Attack Detectioncited by 2
  4. 2025LoRA-Enhanced Vision Transformer for Single Image based Morphing Attack Detection via Knowledge Distillation from EfficientNetcited by 1
  5. 2026Emergent Morphing Attack Detection in Open Multi-modal Large Language Modelscited by 1
  6. 2025Revisiting Diffusion Autoencoder Training for Image Reconstruction Qualitycited by 0
  7. 2025MorphGuard: Morph Specific Margin Loss for Enhancing Robustness to Face Morphing Attackscited by 0
  8. 2025Elytra: A Flexible Framework for Securing Large Vision Systemscited by 0
  9. 2026R-FLoRA: Residual-Statistic-Gated Low-Rank Adaptation for Single-Image Face Morphing Attack Detectioncited by 0
  10. 2026DifFoundMAD: Foundation Models meet Differential Morphing Attack Detectioncited by 0