Skip to main content
SpringerLink
Log in

Unraveling robustness of deep face anti-spoofing models against pixel attacks

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In the last few decades, deep-learning-based face verification and recognition systems have had enormous success in solving complex security problems. However, it has been recently shown that such efficient frameworks are vulnerable to face-spoofing attacks, which has led researchers to build proficient anti-facial-spoofing (or liveness detection) models as an additional security layer. In response, increasingly challenging and tricky attacks have been launched to fool these anti-spoofing mechanisms. In this context, this paper presents the results of an analytical study on transfer-learning-based convolutional neural networks (CNNs) for face liveness detection and differential evolution-based adversarial attacks to evaluate the efficiency of face anti-spoofing classifiers against adversarial attacks. Specifically, experiments were conducted under different use-case scenarios on four face anti-spoofing databases to highlight practical criteria that can be used in the development of countermeasures to address face-spoofing issues.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Atoum Y, Liu Y, Jourabloo A, Liu X (2017) Face anti-spoofing using patch and depth-based CNNs. In: IEEE International Joint Conference on Biometrics (IJCB), pp 319–328

  2. Bose AJ, Aarabi P (2018) Adversarial attacks on face detectors using neural net based constrained optimization. arXiv:180512302

  3. Botelho de Souza G, Papa JP, Marana AN (2018) On the learning of deep local features for robust face spoofing detection. arXiv:180607492

  4. Boulkenafet Z, Komulainen J, Li L, Feng X, Hadid A (2017) OULU-NPU: A mobile face presentation attack database with real-world variations. In: 12th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2017), pp 612–618

  5. Carlini N, Wagner D (2017) Towards evaluating the robustness of neural networks. arXiv:160804644v2

  6. Chen X, Liu C, Li B, Lu K, Song D (2017) Targeted backdoor attacks on deep learning systems using data poisoning. arXiv:171205526

  7. Chingovska I, Anjos A, Marcel S (2012) On the effectiveness of local binary patterns in face anti-spoofing. In: International Conference of Biometrics Special Interest Group (BIOSIG), pp 1–7

  8. Chingovska I, Yang J, Le i Z, Yi D, Li S, Kahm O, Glaser C, Damer N, Kuijper A, Nouak A, Komulainen J, Pereira T, Gupta S, Khandelwal S, Bansal S, Rai A, Krishna T, Goyal D, Waris MA, Zhang H, Ahmad I, Kiranyaz S, Gabbouj M, Tronci R, Pili M, Sirena N, Roli F, Galbally J, Ficrrcz J, Pinto A, Pedrini H, Schwartz W, Rocha A, Anjos A, Marcel S (2013) The 2nd competition on counter measures to 2d face spoofing attacks. In: IAPR Int. Conference on Biometrics (ICB), pp 1–6

  9. Dong Y, Liao F, Pang T, Su H, Zhu J, Hu X, Li J (2018) Boosting adversarial attacks with momentum. arXiv:171006081

  10. Erdogmus N, Marcel S (2013) Spoofing in 2D face recognition with 3d masks and anti-spoofing with kinect. In: IEEE Sixth international conference on biometrics: Theory, Applications and Systems (BTAS), pp 1–6

  11. Feng L, Po L M, Li Y, Xu X, Yuan F, Chun-HoCheung T, Cheung K W (2016) Integration of image quality and motion cues for face anti-spoofing: a neural network approach. J Vis Commun Image Represent 38:451–460

    Article  Google Scholar 

  12. Fourati E, Elloumi W, Chetouani A (2020) Anti-spoofing in face recognition-based biometric authentication using image quality assessment. Multimed Tools Appl 79:865–889

    Article  Google Scholar 

  13. Gan J, Li S, Zhai Y, Liu C (2017) 3D convolutional neural network based on face anti-spoofing. In: 2nd International Conference on Multimedia and Image Processing (ICMIP), pp 1–5

  14. Goodfellow IJ, Shlens J, Szegedy C (2015) Explaining and harnessing adversarial examples. arXiv:14126572

  15. Goswami G, Agarwal A, Ratha N, Singh R, Vatsa M (2019) Detecting and mitigating adversarial perturbations for robust face recognition. Int J Comput Vis (IJCV) 127:719–742

    Article  Google Scholar 

  16. Hadid A (2014) Face biometrics under spoofing attacks: Vulnerabilities, countermeasures, open issues, and research directions. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp 113–118

  17. Hu W, Te G, He J, Chen D, Guo Z (2018) Exploring hypergraph representation on face anti-spoofing beyond 2D attacks. arXiv:181111594

  18. IJCB 2017 competition on generalized face presentation attack detection in mobile authentication scenarios. https://sites.google.com/site/faceantispoofing/, accessed 26 August 2019 (2017)

  19. ISO/IEC 30107-1:2016 information technology biometric presentation attack detection part 1: Framework. https://www.iso.org/standard/53227.html, accessed 26 August 2019 (2016)

  20. Jiawei SVDV, Sakurai K (2019) Attacking convolutional neural network using differential evolution. IPSJ Trans Comput Vis Appl 11:1–12

    Article  Google Scholar 

  21. Jourabloo A, Liu Y, Liu X (2018) Face de-spoofing: Anti-spoofing via noise modeling. arXiv:180709968

  22. Komulainen J (2015) Software-based countermeasures to 2D facial spoofing attacks. PhD thesis, University of Oulu

  23. Kose N, Dugelay JL (2013) On the vulnerability of face recognition systems to spoofing mask attacks. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 2357–2361

  24. Krizhevsky A, Sutskever I, Hinton G E (2017) Imagenet classification with deep convolutionalneural networks. Adv Neural Inf Process Syst (NIPS,) 60:1097–1105

    Google Scholar 

  25. Kurakin A, Goodfellow I, Bengio S (2017a) Adversarial examples in the physical world. arXiv:160702533v4

  26. Kurakin A, Goodfellow I, Bengio S (2017b) Adversarial machine learning at scale. arXiv:161101236v2

  27. Li L, Feng X, Boulkenafet Z, Xia Z, Li M, Hadid A (2016) An original face anti-spoofing approach using partial convolutional neural network. In: Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA), pp 1–6

  28. Li L, Correia P L, Hadid A (2018) Face recognition under spoofing attacks: countermeasures and research directions. IET Biom 7:3–14

    Article  Google Scholar 

  29. Li H, Li W, Cao H, Wang S, Huang F, Kot AC (2018) Unsupervised domain adaptation for face anti-spoofing. IEEE Transactions on Information Forensics and Security 13

  30. Liu Y, Jourabloo A, Liu X (2018) Learning deep models for face anti-spoofing: Binary or auxiliary supervision. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 389–398

  31. Liu Y, Stehouwer J, Jourabloo A, Liu X (2019) Deep tree learning for zero-shot face anti-spoofing. arXiv:190402860

  32. Liu Y, Tai Y, Li J, Ding S, Wang C, Huang F, Li D, Qi W, Ji R (2019) Aurora guard: Real-time face anti-spoofing via light reflection. arXiv:190210311

  33. Liu A, Wan J, Escalera S, Escalante HJ, Tan Z, Yuan Q, Wang K, Lin C, Guo G, Guyon I, Li SZ (2019) Multi-modal face anti-spoofing attack detection challenge at CVPR2019. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops

  34. Lucena O, Junior A, Moia V, Souza R, Valle E, Lotufo R (2017) Transfer learning using convolutional neural networks for face anti-spoofing. In: International Conference Image Analysis and Recognition (ICIAR), pp 27–34

  35. Moosavi-Dezfooli SM, Fawzi A, Fawzi O, Frossard P (2017) Universal adversarial perturbations. arXiv:161008401

  36. Moosavi-Dezfooli SM, Fawzi A, Frossard P (2016) Deepfool: a simple and accurate method to fool deep neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 2574–2582

  37. Nagpal C, Dubey SR (2019) A performance evaluation of convolutional neural networks for face anti spoofing. arXiv:180504176

  38. Nguyen M D, Bui QM (2009) Your face is NOT your password. In: Black hat DC

  39. Papernot N, McDaniel P, Goodfellow IJ, Jha SK, Celik ZB, Swami A (2017) Practical black-box attacks against machine learning. In: ACM on Asia Conference on Computer and Communications Security, pp 506–519

  40. Patel K, Han H, Jain A K (2016) Secure face unlock: Spoof detection on smartphones. IEEE Trans Inf Forens Secur 11:2268–2283

    Article  Google Scholar 

  41. Patel K, Han H, Jain AK (2016) Cross-database face antispoofing with robust feature representation. In: Chinese Conference on Biometric Recognition (CCBR), pp 611–619

  42. Peng F, Qin L, Long M (2018) Face presentation attack detection using guided scale texture. Multimed Tools Appl 77:1–27

    Article  Google Scholar 

  43. Redmon J, Farhadi A (2016) YOLO9000: Better, faster, stronger. arXiv:161208242

  44. Saon G, Kuo HKJ, Rennie S, Picheny M (2015) The IBM 2015 English conversational telephone speech recognition system. arXiv:150505899

  45. Sharif M, Bhagavatula S, Bauer L, Reiter MK (2016) Accessorize to a crime: Real and stealthy attacks on state-of-the-art face recognition. In: ACM SIGSAC Conference on Computer and Communications Security, pp 1528–1540

  46. Sharif M, Bhagavatula S, Bauer L, Reiter MK (2019) A general framework for adversarial examples with objectives. arXiv:180100349

  47. Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. arXiv:14091556

  48. Song Q, Wu Y, Yang L (2018) Attacks on state-of-the-art face recognition using attentional adversarial attack generative network. arXiv:181112026

  49. Souza L, Oliveira L, Pamplona M, Papa J P (2018) How far did we get in face spoofing detection?. Eng Appl Artif Intell 72:368–381

    Article  Google Scholar 

  50. Storn R, Price K (1997) Differential evolution a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11:341–359

    Article  MathSciNet  Google Scholar 

  51. Su J, Vargas DV, Kouichi S (2018) One pixel attack for fooling deep neural networks. arXiv:171008864

  52. Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Rob F (2014) Intriguing properties of neural networks. ICLR, arXiv:13126199

  53. Trusted biometrics under spoofing attacks (TABULA RASA). http://www.tabularasa-euproject.org/, accessed 26 August 2019 (2010)

  54. Tu X, Zhang H, Xie M, Luo Y, Zhang Y, Ma Z (2019) Deep transfer across domains for face anti-spoofing. arXiv:190105633

  55. Tu X, Zhang H, Xie M, Luo Y, Zhang Y, Ma Z (2019) Enhance the motion cues for face anti-spoofing using CNN-LSTM architecture. arXiv:190105635

  56. Unique identification authority of India (UIDAI). https://uidai.gov.in/, accessed 26 August 2019 (2016)

  57. Ur Rehman Y A, Po L M, Liu M, Zou Z, Ou W, Zhao Y (2019) Face liveness detection using convolutional-features fusion of real and deep network generated face images. J Vis Commun Image Represent 59:574–582

    Article  Google Scholar 

  58. Wang Z, Zhao C, Qin Y, Zhou Q, Qi G, Wan J, Lei Z (2019) Exploiting temporal and depth information for multi-frame face anti-spoofing. arXiv:181105118v3

  59. Wen D, Han H, Jain AK (2015) Face spoof detection with image distortion analysis. IEEE Trans Inf Forens Secur 10:746–761

    Article  Google Scholar 

  60. Yang J, Lei Z, Li S Z (2014) Learn convolutional neural network for face anti-spoofing. Computer Science. arXiv:1408.5601, pp 373–384

  61. Zhang Z, Yan J, Liu S, Lei Z, Yi D, Li SZ (2012) A face antispoofing database with diverse attacks. In: 5th IAPR International Conference on Biometrics (ICB), pp 26–31

  62. Zhang K, Zhang Z, Li Z, Qiao Y (2016) Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process Lett 23:1499–1503

    Article  Google Scholar 

  63. Zhou Z, Tang D, Wang X, Han W, Liu X, Zhang K (2018) Invisible mask: Practical attacks on face recognition with infrared. arXiv:180304683

Download references

Acknowledgments

The authors thank the Deanship of Scientific Research and RSSU at King Saud University for their technical support.

Author information

Authors and Affiliations

  1. LRIT - CNRST URAC n∘. 29, Faculty of Sciences Rabat, IT Center, Mohammed V University Morocco, Rabat, Morocco

    Naima Bousnina & Khalid Minaoui

  2. Image Processing Team, Data Science, Shopee Singapore, Singapore, Singapore

    Lilei Zheng

  3. Meridian Team, LYRICA Laboratory, School of Information Sciences, Rabat, Morocco

    Mounia Mikram

  4. Information Technology Department, College of Computer and Information Sciences, King Saud University Riyadh, Riyadh, Kingdom of Saudi Arabia

    Sanaa Ghouzali

Authors
  1. Naima Bousnina
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lilei Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mounia Mikram
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sanaa Ghouzali
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Khalid Minaoui
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Naima Bousnina.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Bousnina, N., Zheng, L., Mikram, M. et al. Unraveling robustness of deep face anti-spoofing models against pixel attacks. Multimed Tools Appl 80, 7229–7246 (2021). https://doi.org/10.1007/s11042-020-10041-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-10041-1

Keywords

Search

Navigation