Abstract
As the world continues to grapple with the COVID-19 pandemic, the face mask detection system has become an essential tool in containing the spread of the virus. However, our study has demonstrated that existing deep learning-based face mask detection models are vulnerable to adversarial attacks, which can severely compromise their performance and lead to misclassification. This study investigates the robustness of three face mask detection models based on state-of-the-art convolutional neural networks (CNNs), namely MobileNetV2, ResNet50, and EfficientNet-B2, against such attacks and propose a novel, more robust face mask detection algorithm that is resilient to adversarial attacks. We evaluated the models based on several performance metrics, including precision, recall, F1 score, and accuracy, and then subjected them to two popular adversarial attack techniques: fast gradient sign method (FGSM) and projected gradient descent (PGD). The results indicate that the adversarial attacks caused a substantial reduction in the accuracy of the models, with MobileNetV2 decreasing from 95.83–14.83% and 0% (under FGSM and PGD attacks, respectively), ResNet50 decreasing from 96.48–13.97% and 0% (under FGSM and PGD attacks, respectively), and EfficientNet-B2 decreasing from 95.56–15.53% and 0% (under FGSM and PGD attacks, respectively). Finally, we illustrated that the proposed robust algorithm enhanced the model’s resistance to adversarial attacks. These findings highlight the urgent need to raise awareness about adversarial attacks targeting COVID-19 monitoring systems and urge proactive measures to safeguard healthcare systems from similar threats before practical deployment.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available in the KAGGLE repository, https://www.kaggle.com/datasets/shiekhburhan/face-mask-dataset.
Code availability
The code generated during and/or analyzed during the current study is available from the corresponding author on reasonable request.
Change history
14 September 2023
A Correction to this paper has been published: https://doi.org/10.1007/s12530-023-09537-6
References
Agrawal T, Choudhary P (2022) FocusCovid: automated COVID-19 detection using deep learning with chest X-ray images. Evol Syst 13:519–533. https://doi.org/10.1007/s12530-021-09385-2
Alhares H, Tanha J, Balafar MA (2023) AMTLDC: a new adversarial multi-source transfer learning framework to diagnosis of COVID-19. Evol Syst. https://doi.org/10.1007/s12530-023-09484-2
Bania RK (2023), February 1 Ensemble of deep transfer learning models for real-time automatic detection of face mask. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-023-14408-y
Bu W, Xiao J, Zhou C, Yang M, Peng C (2017) A cascade framework for masked face detection. In: IEEE international conference on cybernetics and intelligent systems (CIS) and IEEE conference on robotics, automation and mechatronics (RAM). IEEE; 2017. pp 458–62
Cabani A, Hammoudi K, Benhabiles H, Melkemi M (2021) MaskedFace-Net–a dataset of correctly/incorrectly masked face images in the context of COVID-19. Smart Health 19:100144
Co KT, Muñoz-González L, de Maupeou S, Lupu EC (2019), November Procedural noise adversarial examples for black-box attacks on deep convolutional networks. In: Proceedings of the 2019 ACM SIGSAC conference on computer and communications security, pp 275–289
Chae S, Kwon S, Lee D (2018) Predicting infectious disease using deep learning and big data. Int J Environ Res Public Health 15(8):1596
C. GitHub - chandrikadeb7/Face-Mask-Detection: Face Mask Detection system based on computer vision and deep learning using OpenCV and Tensorflow/Keras. GitHub. https://github.com/chandrikadeb7/Face-Mask-Detection
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009), June Imagenet: A large-scale hierarchical image database]. In 2009 IEEE conference on computer vision and pattern recognition, pp 248–255, IEEE
Deng J, Guo J, Xue N, Zafeiriou S (2021) “Arcface-MFnet: Additive Angular Margin Loss for Deep Face Recognition with Masked Faces,“ in 2021 IEEE International Conference on Computer Vision Workshop (ICCVW), Oct. pp 4342–4351
Ejaz MS, Islam MR, Sifatullah M, Sarker A (2019) Implementation of principal component analysis on masked and non-masked face recognition. In: 2019 1st international conference on advances in science, engineering and robotics technology (ICASERT). IEEE, pp 1–5
Ellis R (2020) WHO changes stance, says public should wear masks. World Health Organization
Face Mask Dataset. Face Mask Dataset | Kaggle. /datasets/shiekhburhan/face-mask-dataset
Face Mask Detection Kaggle Dataset(2020) https://www.kaggle.com/andrewmvd/face-mask-detection. Accessed: Feb. 18, 2023
Feng S, Shen C, Xia N, Song W, Fan M, Cowling BJ (2020) Rational use of face masks in the COVID-19 pandemic. The Lancet Respiratory Medicine 8(5):434–436
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., ... & Lempitsky, V. (2016). Domain-adversarial training of neural networks. The journal of machine learning research, 17(1), 2096-2030
Ge S, Li J, Ye Q, Luo Z (2017) “Detecting masked faces in the wild with lle-cnns,“ in Proceedings of the IEEE conference on computer vision and pattern recognition, pp.2682–2690
Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572
Gougeh RA (2021) How Adversarial attacks affect Deep Neural Networks Detecting COVID-19? Research Square. https://doi.org/10.21203/rs.3.rs-763355/v1
Hirano H, Koga K, Takemoto K (2020) Vulnerability of deep neural networks for detecting COVID-19 cases from chest X-ray images to universal adversarial attacks, PLoS ONE 15 (12)
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Jain AK, Duin RPW, Mao J (2000) Statistical pattern recognition: a review. IEEE Trans Pattern Anal Mach Intell 22(1):4–37
Jayaswal R, Dixit M (2022) September 8). AI-based face mask detection system: a straightforward proposition to fight with Covid-19 situation. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-022-13697-z
Kakizaki K, Yoshida K (2019) Adversarial image translation: Unrestricted adversarial examples in face recognition systems. arXiv preprint arXiv:1905.03421
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst, 25
Li Y, Wang R, Yang Z (2022) Optimal scheduling of isolated Microgrids using automated reinforcement learning-based multi-period forecasting. IEEE Trans Sustain Energy 13(1):159–169
Liang Z, Wen G, Guo Y (2020) “MFRD: A Large-Scale Multi-View Masked Face Recognition Dataset,“ in arXiv preprint arXiv:2012.00707,
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: Single Shot MultiBox Detector. Computer Vision – ECCV 2016, 21–37. https://doi.org/10.1007/978-3-319-46448-0_2
Li Y, Wei X, Li Y, Dong Z, Shahidehpour M (2022) Detection of False Data Injection Attacks in Smart Grid: A Secure Federated Deep Learning Approach. IEEE Trans on Smart Grid 13(6):4862–4872
Loey M, Manogaran G, Taha MHN, Khalifa NEM (2021) A hybrid deep transfer learning model with machine learning methods for face mask detection in the era of the COVID-19 pandemic. Measurement 167:108288
Lu X, Xu Y, Yuan W (2023) PDRF-Net: a progressive dense residual fusion network for COVID-19 lung CT image segmentation. Evol Syst. https://doi.org/10.1007/s12530-023-09489-x
Madry A, Makelov A, Schmidt L, Tsipras D, Vladu A (2017) Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv :1706.06083
Medical mask dataset.https://www.kaggle.com/shreyashwaghe/medical-mask-dataset. Accessed 17 Jun 2021
Pal B, Gupta D, Rashed-Al-Mahfuz M, Alyami SA, Moni MA (2021) Vulnerability in deep transfer learning models to adversarial fast gradient sign attack for covid-19 prediction from chest radiography images. Appl Sci 11(9):4233
Qi G, Gong L, Song Y, Ma K, Zheng Y (2021) Stabilized medical image attacks. arXiv preprint arXiv :2103.05232
Qin B, Li D (2020) Identifying facemask-wearing condition using image super-resolution with classification network to prevent COVID-19. Sensors 20(18):5236
Rahman A, Hossain MS, Alrajeh NA, Alsolami F (2020) Adversarial examples—security threats to COVID-19 deep learning systems in medical IoT devices. IEEE Internet of Things Journal 8(12):9603–9610
Redmon J, Farhadi A (2018) Yolov3: an incremental improvement. arXiv preprint arXiv :1804.02767
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510–4520
Sheikh B, Zafar ARRFMDS (2023) Rapid Real-Time face Mask Detection System for effective COVID-19 monitoring. SN COMPUT SCI 4:288. https://doi.org/10.1007/s42979-023-01738-9
Sheikh BUh, Zafar A (2023) Untargeted white-box adversarial attack to break into deep leaning based COVID-19 monitoring face mask detection system. Multimed Tools Appl. https://doi.org/10.1007/s11042-023-15405-x
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818–2826
Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan GI, Fergus R (2013) (n.d.) Intriguing properties of neural networks. arXiv arXiv:1312.6199
Su X, Gao M, Ren J, Li Y, Dong M, Liu X (2021) December 9). Face mask detection and classification via deep transfer learning. Multimedia Tools and Applications 81(3):4475–4494. https://doi.org/10.1007/s11042-021-11772-5
Tan M, Le QV (2019) EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, 9–15 June 2019, 6105–6114. http://proceedings.mlr.press/v97/tan19a.html
Ullah N, Javed A, Ali Ghazanfar M, Alsufyani A, Bourouis S (2022) November). A novel DeepMaskNet model for face mask detection and masked facial recognition. J King Saud Univ - Comput Inform Sci 34(10):9905–9914. https://doi.org/10.1016/j.jksuci.2021.12.017
Ul Haque SB, Zafar A, Roshan K (2023) Security Vulnerability in Face Mask Monitoring System. In: 10th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, 2023, pp 231–237
Viola P, Jones M (2001), December Rapid object detection using a boosted cascade of simple features. In Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001, Vol.1, pp I-I, IEEE.
Wang L, Lin ZQ, Wong A (2020) Covid-net: a tailored deep convolutional neural network design for detection of covid-19 cases from chest x-ray images. Sci Rep 10(1):1–12
Wang Z, Wang G, Huang B, Xiong Z, Hong Q, Wu H, Yi P, Jiang K, Wang N, Pei Y et al “Masked face recognition dataset and application,“ arXiv preprint arXiv:2003.09093, 2020. [Online]. Available: arXiv:2003.09093
World Health Organization (2020) Advice on the use of masks in the context of COVID-19: interim guidance, 6 April 2020 (no. WHO/2019-nCov/IPC_Masks/2020.3). World Health Organization
Xing H, Xiao Z, Zhan D, Luo S, Dai P, Li K (2022) July 13). SelfMatch: robust semisupervised time-series classification with self‐distillation. Int J Intell Syst 37(11):8583–8610. https://doi.org/10.1002/int.22957
Xiao Z, Zhang H, Tong H, Xu X An Efficient Temporal Network with Dual Self-Distillation for Electroencephalography Signal Classification. 2022 IEEE International Conference on, Bioinformatics (2022), December 6 and Biomedicine (BIBM). https://doi.org/10.1109/bibm55620.2022.9995049
Xie W, Mou W, Zhao F, Feng J (2021) WIDER FACE MASK: A Face Mask Detection Benchmark. In:2021 IEEE International Conference on Computer Vision (ICCV), pp 8828–8837
Yaman S, Karakaya B, Erol Y (2022) A novel normalization algorithm to facilitate pre-assessment of Covid-19 disease by improving accuracy of CNN and its FPGA implementation. Evol Syst. https://doi.org/10.1007/s12530-022-09419-3]
Yang S, Luo P, Loy CC, Tang X (2016) Wider face: a face detection benchmark. In: Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE; p.5525–33
Yapıcı MM, Tekerek A, Topaloğlu N (2019) October Performance comparison of convolutional neural network models on GPU. In: 2019 IEEE 13th International Conference on Application of Information and Communication Technologies (AICT) pp 1–4, IEEE
Zhang H, Xie W, Zhu X, Mou W, Feng J (2021) CelebMask-HQ: A Large-Scale Face Mask Dataset with Celebrities. In: 2021 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pp 3251–3259
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The original online version of this article was revised due to change in symbols in the equations on page 8 and 9.
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
sheikh, B., Zafar, A. Beyond accuracy and precision: a robust deep learning framework to enhance the resilience of face mask detection models against adversarial attacks. Evolving Systems 15, 1–24 (2024). https://doi.org/10.1007/s12530-023-09522-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12530-023-09522-z