mlsanityData to 14 Oct 2026

SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems

arXiv 2507.01607 ↗First posted 2 Jul 2025cs.CV cs.AI cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

The widespread deployment of Deep Learning-based Face Recognition Systems raises many security concerns. While prior research has identified backdoor vulnerabilities on isolated components, Backdoor Attacks on real-world, unconstrained pipelines remain underexplored. This SoK paper presents the first comprehensive system-level analysis and measurement of the impact of Backdoor Attacks on fully-fledged Face Recognition Systems. We combine the existing Supervised Learning backdoor literature targeting face detectors, face antispoofing, and face feature extractors to demonstrate a system-level vulnerability. By analyzing 20 pipeline configurations and 15 attack scenarios in a holistic manner, we reveal that an attacker only needs a single backdoored model to compromise an entire Face Recognition System. Finally, we discuss the impact of such attacks and propose best practices and countermeasures for stakeholders.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 43 of its 84 references that are in the map. First posted on arXiv 2 Jul 2025.

Builds on

43 of 84 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2017Squeeze-and-Excitation Networkscited by 4,789
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  6. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  7. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  8. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 971
  9. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 914
  10. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 903
  11. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 737
  12. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 624
31 more
  1. 2020Backdoor Learning: A Surveycited by 426
  2. 2015WIDER FACE: A Face Detection Benchmarkcited by 298
  3. 2019Label-Consistent Backdoor Attackscited by 296
  4. 2023Poisoning Web-Scale Training Datasets is Practicalcited by 290
  5. 2017Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environmentscited by 260
  6. 2019A new Backdoor Attack in CNNs by training set corruption without label poisoningcited by 242
  7. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 232
  8. 2018MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devicescited by 182
  9. 2020Backdoor Attacks Against Deep Learning Systems in the Physical Worldcited by 134
  10. 2020CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotationscited by 109
  11. 2019Biometric Face Presentation Attack Detection with Multi-Channel Convolutional Neural Networkcited by 79
  12. 2021Manipulating SGD with Data Ordering Attackscited by 74
  13. 2021CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiabilitycited by 69
  14. 2021Deep Learning for Face Anti-Spoofing: A Surveycited by 65
  15. 2018ArcFace: Additive Angular Margin Loss for Deep Face Recognitioncited by 56
  16. 2022BadDet: Backdoor Attacks on Object Detectioncited by 45
  17. 2020Backdoor Attacks against Transfer Learning with Pre-trained Deep Learning Modelscited by 44
  18. 2021Face.evoLVe: A High-Performance Face Recognition Librarycited by 26
  19. 2023Backdoor Attack with Sparse and Invisible Triggercited by 20
  20. 2021Going Deeper Into Face Detection: A Surveycited by 10
  21. 2021A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verificationcited by 10
  22. 2022A temporal chrominance trigger for clean-label backdoor attack against anti-spoof rebroadcast detectioncited by 10
  23. 2021Master Face Attacks on Face Recognition Systemscited by 7
  24. 2022On the (Limited) Generalization of MasterFace Attacks and Its Relation to the Capacity of Face Representationscited by 7
  25. 2022State of the Art of Quality Assessment of Facial Imagescited by 5
  26. 2022RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNNcited by 4
  27. 2024Rethinking the Vulnerabilities of Face Recognition Systems:From a Practical Perspectivecited by 4
  28. 2013Image-based Face Detection and Recognition: "State of the Art"cited by 2
  29. 2022An anomaly detection approach for backdoored neural networks: face recognition as a case studycited by 2
  30. 2024Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systemscited by 2
  31. 2024Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Taskscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Resurrecting Trust in Facial Recognition: Mitigating Backdoor Attacks in Face Recognition to Prevent Potential Privacy Breaches
  2. 2025Backdoor Poisoning Attack Against Face Spoofing Attack Detection Methods
  3. 2024Countering Backdoor Attacks in Image Recognition: A Survey and Evaluation of Mitigation Strategies
  4. 2024MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup Transfer
  5. 2023Facial Misrecognition Systems: Simple Weight Manipulations Force DNNs to Err Only on Specific Persons
  6. 2025From Detection to Correction: Backdoor-Resilient Face Recognition via Vision-Language Trigger Detection and Noise-Based Neutralization
  7. 2023SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification
  8. 2025Backdoor Attacks on Deep Learning Face Detection