Abstract
Despite the promising results achieved by deep iris presentation attack detection (PAD) in dataset-specific scenarios, the advanced approach remains vulnerable to novel attacks. Real-world attacks evolve over time. Typically, fine-tuning and retraining from scratch are employed to incrementally learn new attacks. However, fine-tuning degrades performance on old attacks, i.e., catastrophic forgetting. Retraining on all data is unavailable due to data privacy. To address these issues, we are the first to propose a lifelong iris PAD to incrementally learn new attacks without storing old data. Our approach utilizes a prompt pool to preserve attack-independent and attack-shared knowledge, wherein learnable prompts aid in prediction by the pre-trained Vision Transformer (ViT). Furthermore, adaptive attention masks for sequential new attacks are applied to pre-trained ViT. Consequently, our method improves plasticity while preserving stability. Extensive experiments are performed on our building dataset combing IITD and CASIA to evaluate iris PAD in incremental learning. Our proposed method obtains competitive performance over state-of-the-art Iris PAD schemes.
Similar content being viewed by others
References
Rajeev Kumar M, Arthi K (2020) An effective non-cooperative iris recognition system using hierarchical collaborative representation-based classification. J Supercomput 76(8):5835–5848
Zhao Z, Kumar A (2017) Towards more accurate iris recognition using deeply learned spatially corresponding features. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3809–3818
Chang Y-T, Shih TK, Li Y-H, Kumara W (2020) Effectiveness evaluation of iris segmentation by using geodesic active contour (GAC). J Supercomput 76(3):1628–1641
Proença H, Neves JC (2017) Irina: Iris recognition (even) in inaccurately segmented data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 538–547 (2017)
Rostami M, Spinoulas L, Hussein M, Mathai J, Abd-Almageed W (2021) Detection and continual learning of novel face presentation attacks. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 14851–14860
Czajka A, Bowyer KW (2018) Presentation attack detection for iris recognition: an assessment of the state-of-the-art. ACM Comput Surv (CSUR) 51(4):1–35
Chen C, Ross A (2021) An explainable attention-guided iris presentation attack detector. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp 97–106
Yadav S, Ross A (2021) CIT-GAN: cyclic image translation generative adversarial network with application in iris presentation attack detection. In: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pp 2412–2421
Das P, McFiratht J, Fang Z, Boyd A, Jang G, Mohammadi A, Purnapatra S, Yambay D, Marcel S, Trokielewicz M et al (2020) Iris liveness detection competition (LivDet-Iris)—the 2020 edition. In: 2020 IEEE International Joint Conference on Biometrics (IJCB), pp 1–9
Pérez-Cabo D, Jiménez-Cabello D, Costa-Pazo A, López-Sastre RJ (2020) Learning to learn face-pad: a lifelong learning approach. In: 2020 IEEE International Joint Conference on Biometrics (IJCB), pp 1–9
French RM (1999) Catastrophic forgetting in connectionist networks. Trends Cogn Sci 3(4):128–135
Ramasesh VV, Lewkowycz A, Dyer E (2021) Effect of scale on catastrophic forgetting in neural networks. In: International Conference on Learning Representations
De Lange M, Aljundi R, Masana M, Parisot S, Jia X, Leonardis A, Slabaugh G, Tuytelaars T (2021) A continual learning survey: defying forgetting in classification tasks. IEEE Trans Pattern Anal Mach Intell 44(7):3366–3385
Tiwari R, Killamsetty K, Iyer R, Shenoy P (2022) GCR: Gradient coreset based replay buffer selection for continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 99–108
Wang L, Zhang X, Yang K, Yu L, Li C, Lanqing H, Zhang S, Li Z, Zhong Y, Zhu J (2021) Memory replay with data compression for continual learning. In: International Conference on Learning Representations
Jin X, Sadhu A, Du J, Ren X (2021) Gradient-based editing of memory examples for online task-free continual learning. Adv Neural Inf Process Syst 34:29193–29205
Liu P, Yuan W, Fu J, Jiang Z, Hayashi H, Neubig G (2021) Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. arXiv preprint arXiv:2107.13586
Wang Z, Zhang Z, Lee C-Y, Zhang H, Sun R, Ren X, Su G, Perot V, Dy J, Pfister T (2022) Learning to prompt for continual learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 139–149
Zhou K, Yang J, Loy CC, Liu Z (2022) Conditional prompt learning for vision-language models. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 16816–16825
Han X, Zhao W, Ding N, Liu Z, Sun M (2021) PTR: prompt tuning with rules for text classification. arXiv preprint arXiv:2105.11259
Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth \(16\times 16\) words: transformers for image recognition at scale. In: International Conference on Learning Representations
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser Ł, Polosukhin I (2017) Attention is all you need. In: Advances in Neural Information Processing Systems, vol 30
Mallya A, Davis D, Lazebnik S (2018) Piggyback: adapting a single network to multiple tasks by learning to mask weights. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 67–82
Daugman J (2000) Wavelet demodulation codes, statistical independence, and pattern recognition. Institute of Mathematics and its Applications. In: Blackledge, Turner (eds) Proceedings of the 2nd IMA-IP: Mathematical Methods, Algorithms, and Applications, pp 244–260
Lee EC, Park KR, Kim J (2006) Fake iris detection by using Purkinje image. In: International Conference on Biometrics. Springer, Berlin, pp 397–403
Czajka A (2015) Pupil dynamics for iris liveness detection. IEEE Trans Inf Forensics Secur 10(4):726–735
Connell J, Ratha N, Gentile J, Bolle R (2013) Fake iris detection using structured light. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp 8692–8696
He Z, Sun Z, Tan T, Wei Z (2009) Efficient iris spoof detection via boosted local binary patterns. In: International Conference on Biometrics. Springer, Berlin, pp 1080–1090
Raghavendra R, Busch C (2015) Robust scheme for iris presentation attack detection using multiscale binarized statistical image features. IEEE Trans Inf Forensics Secur 10(4):703–715
Fathy WS-A, Ali HS (2018) Entropy with local binary patterns for efficient iris liveness detection. Wirel Pers Commun 102(3):2331–2344
Fang Z, Czajka A, Bowyer KW (2020) Robust iris presentation attack detection fusing 2D and 3D information. IEEE Trans Inf Forensics Secur 16:510–520
Silva P, Luz E, Baeta R, Pedrini H, Falcao AX, Menotti D (2015) An approach to iris contact lens detection based on deep image representations. In: 2015 28th SIBGRAPI Conference on Graphics, Patterns and Images, IEEE. pp 157–164
Menotti D, Chiachia G, Pinto A, Schwartz WR, Pedrini H, Falcao AX, Rocha A (2015) Deep representations for iris, face, and fingerprint spoofing detection. IEEE Trans Inf Forensics Secur 10(4):864–879
Pala F, Bhanu B (2017) Iris liveness detection by relative distance comparisons. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp 162–169
Long M, Zeng Y (2019) Detecting iris liveness with batch normalized convolutional neural network. Comput Mater Contin 58(2):493–504
Choudhary M, Tiwari V, Uduthalapally V (2021) Iris presentation attack detection based on best-k feature selection from yolo inspired RoI. Neural Comput Appl 33(11):5609–5629
Jang E, Gu S, Poole B (2016) Categorical reparameterization with Gumbel-Softmax. arXiv preprint arXiv:1611.01144 (2016)
Yadav D, Kohli N, Doyle JS, Singh R, Vatsa M, Bowyer KW (2014) Unraveling the effect of textured contact lenses on iris recognition. IEEE Trans Inf Forensics Secur 9(5):851–862
Gupta P, Behera S, Vatsa M, Singh, R (2014) On iris spoofing using print attack. In: 2014 22nd International Conference on Pattern Recognition, IEEE. pp 1681–1686
Wei Z, Tan T, Sun Z (2008) Synthesis of large realistic iris databases using patch-based sampling. In: 2008 19th International Conference on Pattern Recognition, IEEE, pp 1–4
Kumar A, Passi A (2010) Comparison and combination of iris matchers for reliable personal authentication. Pattern Recogn 43(3):1016–1026
Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, Jégou H (2021) Training data-efficient image transformers and distillation through attention. In: International Conference on Machine Learning, PMLR. pp 10347–10357
Pham Q, Liu C, Hoi S (2021) Dualnet: continual learning, fast and slow. Adv Neural Inf Process Syst 34:16131–16144
Serra J, Suris D, Miron M, Karatzoglou A (2018) Overcoming catastrophic forgetting with hard attention to the task. In: International Conference on Machine Learning. PMLR, pp 4548–4557
Cha H, Lee J, Shin J (2021) Co2l: contrastive continual learning. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp 9516–9525
Fang M, Damer N, Boutros F, Kirchbuchner F, Kuijper A (2021) Iris presentation attack detection by attention-based and deep pixel-wise binary supervision network. In: 2021 IEEE International Joint Conference on Biometrics (IJCB), pp 1–8
Acknowledgments
This research was funded by the National Natural Science Foundation of China (Grant Number 61471181), the Natural Science Foundation of Jilin Province (Grant Number YDZJ202101ZYTS144), the Jilin Province Industrial Innovation Special Fund Project (Grant Number 2019C053-2), and the Science and Technology Project of the Jilin Provincial Education Department (Grant Number JJKH20180448KJ). Thanks to the Jilin Provincial Key Laboratory of Biometrics New Technology for supporting this research.
Author information
Authors and Affiliations
Contributions
ZZ wrote the main manuscript text. YL, XZ, and SL provided the main ideas and methods. SZ and YL prepared figures and tables. ZL corrected grammar and formatting. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing financial interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhou, Z., Liu, Y., Zhu, X. et al. Lifelong iris presentation attack detection without forgetting. J Supercomput 80, 1–19 (2024). https://doi.org/10.1007/s11227-023-05445-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-023-05445-3