Skip to main content

Advertisement

Springer Nature Link
Log in

CNN-based continuous authentication for digital therapeutics using variational autoencoder

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Digital therapeutics (DTx) can be used in conjunction with wearable devices to continuously collect, transmit, and analyze patients’ physiological data, achieving personalized precision medicine. In practice, security and privacy problems may arise when physiological data are improperly protected. For instance, any inaccuracies exist in the collected data (due to malicious attacks or mistakes) may affect the effectiveness of treatment. Additionally, physiological data are characterized by a small amount, resulting in decreased authentication accuracy of deep learning models. Inspired by these observations, this paper presents a continuous authentication scheme for digital therapeutics using variational autoencoder and convolutional neural network (VAECNN). Typically, in the training phase, to improve the stability of CNN model, the collected data are used for data augmentation using VAE. To train a one-class classifier, optimal features are selected by conducting principal component analysis (PCA). During the continuous authentication phase, the trained CNN is utilized for feature extraction. Subsequently, the trained one-class classifier is employed to authenticate the user as a legitimate user or an impostor. To assess the performance of VAECNN, we conduct extensive experiments to estimate its performance, the performance of VAE augmentation and the designed CNN, and compare it with several augmentation schemes and representative authentication schemes. Experimental results indicate that our VAECNN achieves the best performance with elliptic envelope (EE) classifier, i.e., it achieves the lowest equal error rate (EER) of 1.06% and the highest accuracy of 98.96%.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 6

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Data availability

No datasets were generated or analyzed during the current study.

Notes

  1. Until now, types of one-time authentication mechanisms have been developed and employed. Our scheme aims to develop a continuous authentication scheme, and any secure one-time authentication mechanism can be employed to achieve initial authentication. Thus, in initial login authentication of our scheme, a secure one-time authentication mechanism is employed without introducing the detailed processes.

  2. According to [43], the average bitstrength of users chosen passwords is around 40.54 bits.

References

  1. Dang A, Arora D, Rane P (2020) Role of digital therapeutics and the changing future of healthcare. J Family Med Primary Care 9(5):2207

    Article  Google Scholar 

  2. Dang A, Dang D, Rane P (2021) The expanding role of digital therapeutics in the post-COVID-19 era. Open COVID J 1(1):32–37

    Article  Google Scholar 

  3. Tang W, Zhang K, Ren J, Zhang Y, Shen X (2019) Flexible and efficient authenticated key agreement scheme for bans based on physiological features. IEEE Trans Mob Comput 18(4):845–856. https://doi.org/10.1109/TMC.2018.2848644

    Article  Google Scholar 

  4. Seyedi M, Kibret B, Lai DTH, Faulkner M (2013) A survey on intrabody communications for body area network applications. IEEE Trans Biomed Eng 60(8):2067–2079. https://doi.org/10.1109/TBME.2013.2254714

    Article  Google Scholar 

  5. Zhang J, Pan L, Han Q, Chen C, Wen S, Xiang Y (2022) Deep learning based attack detection for cyber-physical system cybersecurity: a survey. IEEE CAA J Automatica Sinica 9(3):377–391

    Article  Google Scholar 

  6. Chen X, Li C, Wang D, Wen S, Zhang J, Nepal S, Xiang Y, Ren K (2020) Android HIV: a study of repackaging malware for evading machine-learning detection. IEEE Trans Inf Forensics Secur 15:987–1001

    Article  Google Scholar 

  7. Pycroft L, Boccard SG, Owen SL, Stein JF, Fitzgerald JJ, Green AL, Aziz TZ (2016) Brainjacking: implant security issues in invasive neuromodulation. World Neurosurg 92:454–462

    Article  Google Scholar 

  8. Sequeiros JB, Chimuco FT, Samaila MG, Freire MM, Inácio PR (2020) Attack and system modeling applied to Iot, cloud, and mobile ecosystems: embedding security by design. ACM Comput Surv (CSUR) 53(2):1–32

    Article  Google Scholar 

  9. Imtiaz SI, Rehman S, Javed AR, Jalil Z, Liu X, Alnumay WS (2021) Deepamd: detection and identification of android malware using high-efficient deep artificial neural network. Futur Gener Comput Syst 115:844–856

    Article  Google Scholar 

  10. Baig AF, Eskeland S (2021) Security, privacy, and usability in continuous authentication: a survey. Sensors 21(17):5967

    Article  Google Scholar 

  11. Stylios I, Kokolakis S, Thanou O, Chatzis S (2021) Behavioral biometrics & continuous user authentication on mobile devices: a survey. Inf Fusion 66:76–99

    Article  Google Scholar 

  12. Liang Y, Samtani S, Guo B, Yu Z (2020) Behavioral biometrics for continuous authentication in the internet-of-things era: an artificial intelligence perspective. IEEE Internet Things J 7(9):9128–9143

    Article  Google Scholar 

  13. Gonzalez-Manzano L, Fuentes JMD, Ribagorda A (2019) Leveraging user-related internet of things for continuous authentication: a survey. ACM Comput Surv (CSUR) 52(3):1–38

    Article  Google Scholar 

  14. Lin C, He J, Shen C, Li Q, Wang Q (2022) Crossbehaauth: cross-scenario behavioral biometrics authentication using keystroke dynamics. IEEE Trans Depend Secure Comput 20(3):2314–2327

    Google Scholar 

  15. Niinuma K, Park U, Jain AK (2010) Soft biometric traits for continuous user authentication. IEEE Trans Inf Forensics Secur 5(4):771–780

    Article  Google Scholar 

  16. Liao R-F, Wen H, Chen S, Xie F, Pan F, Tang J, Song H (2019) Multiuser physical layer authentication in internet of things with data augmentation. IEEE Internet Things J 7(3):2077–2088

    Article  Google Scholar 

  17. Li Y, Hu H, Zhou G (2018) Using data augmentation in continuous authentication on smartphones. IEEE Internet Things J 6(1):628–640

    Article  Google Scholar 

  18. Li Y, Hu H, Zhou G, Deng S (2018) Sensor-based continuous authentication using cost-effective kernel ridge regression. IEEE Access 6:32554–32565

    Article  Google Scholar 

  19. Li Y, Luo J, Deng S, Zhou G (2021) CNN-based continuous authentication on smartphones with conditional Wasserstein generative adversarial network. IEEE Internet Things J 9(7):5447–5460

    Article  Google Scholar 

  20. Li Y, Liu L, Deng S, Qin H, El-Yacoubi MA, Zhou G (2024) Memory-augmented autoencoder based continuous authentication on smartphones with conditional transformer GANS. IEEE Trans Mob Comput 23(5):4467–4482

    Article  Google Scholar 

  21. Fereidooni H, König J, Rieger P, Chilese M, Gökbakan B, Finke M, Dmitrienko A, Sadeghi A (2023) Authentisense: A scalable behavioral biometrics authentication scheme using few-shot learning for mobile platforms. In: 30th Annual Network and Distributed System Security Symposium, NDSS2023, San Diego, California, USA, February 27 - March 3, 2023

  22. Yang Z, Li Y, Zhou G (2024) Unsupervised sensor-based continuous authentication with low-rank transformer using learning-to-rank algorithms. IEEE Trans Mob Comput 23(9):8839–8854. https://doi.org/10.1109/TMC.2024.3353209

    Article  Google Scholar 

  23. Li Y, Liu L, Qin H, Deng S, El-Yacoubi MA, Zhou G (2023) Adaptive deep feature fusion for continuous authentication with data augmentation. IEEE Trans Mob Comput 22(10):5690–5705. https://doi.org/10.1109/TMC.2022.3186614

    Article  Google Scholar 

  24. Hu M, Zhang K, You R, Tu B (2023) Multisensor-based continuous authentication of smartphone users with two-stage feature extraction. IEEE Internet Things J 10(6):4708–4724. https://doi.org/10.1109/JIOT.2022.3219135

    Article  Google Scholar 

  25. Li Y, Luo J, Deng S, Zhou G (2023) Searchauth: neural architecture search-based continuous authentication using auto augmentation search. ACM Trans Sens Netw 19(4):92–19223

    Article  Google Scholar 

  26. Deng S, Luo J, Li Y (2021) CNN-based continuous authentication on smartphones with auto augmentation search. In: Gao D, Li Q, Guan X, Liao X (eds) Information and Communications Security. Springer, Cham, pp 169–186

    Chapter  Google Scholar 

  27. Wagata K, Teoh ABJ (2022) Few-shot continuous authentication for mobile-based biometrics. Appl Sci 12(20):10365

    Article  Google Scholar 

  28. Yang Z, Li Y, Zhou G (2023) TS-GAN: time-series GAN for sensor-based health data augmentation. ACM Trans Comput Heal 4(2):12–11221

    Google Scholar 

  29. Vidya B, Sasikumar P (2022) Wearable multi-sensor data fusion approach for human activity recognition using machine learning algorithms. Sens Actuators, A 341:113557

    Article  Google Scholar 

  30. Kashinath SA, Mostafa SA, Mustapha A, Mahdin H, Yang TJ (2021) Review of data fusion methods for real-time and multi-sensor traffic flow analysis. IEEE Access 99:1–1

    Google Scholar 

  31. Frank J, Mannor S, and Precup D Data sets: mobile phone gait recognition data, 2010. http://www.cs.mcgill.ca/~ifrank8/data/gait-dataset.html

  32. Sztyler T, Stuckenschmidt H (2016) On-body localization of wearable devices: An investigation of position-aware activity recognition. In: 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom), pp. 1–9. IEEE

  33. Doersch C (2016) Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908

  34. Atienza R (2018) Advanced deep learning with Keras: apply deep learning techniques, autoencoders, GANs, variational autoencoders. policy gradients, and more, deep reinforcement learning

  35. Kingma DP, Welling M (2019) An introduction to variational autoencoders. Found Trends® Mach Learn 12(4):307–392

    Article  Google Scholar 

  36. Breunig MM, Kriegel H-P, Ng RT, Sander (2000) Lof: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pp. 93–104

  37. Liu FT, Ting KM, Zhou Z-H (2008) Isolation forest. In: 2008 Eighth IEEE International Conference on Data Mining, pp. 413–422. IEEE

  38. EStimator D (1999) A fast algorithm for the minimum covariance. Technometrics 41(3):212

    Article  Google Scholar 

  39. Schölkopf B, Williamson RC, Smola AJ, Shawe-Taylor J, Platt JC (1999) Support vector method for novelty detection. In: Solla, S.A., Leen, T.K., Müller, K. (eds.) Advances in Neural Information Processing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29 - December 4, 1999], pp 582–588

  40. Breunig MM, Kriegel H-P, Ng RT, Sander J (2000) LOF: identifying density-based local outliers. In: Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pp 93–104

  41. Liu FT, Ting KM, Zhou Z-H (2012) Isolation-based anomaly detection. ACM Trans Knowl Discov Data (TKDD) 6(1):1–39

    Article  Google Scholar 

  42. Qin H, El-Yacoubi MA, Li Y, Liu C (2021) Multi-scale and multi-direction GAN for CNN-based single palm-vein identification. IEEE Trans Inf Forensics Secur 16:2652–2666. https://doi.org/10.1109/TIFS.2021.3059340

    Article  Google Scholar 

  43. Florêncio DAF, Herley C (2007) A large-scale study of web password habits. In: Williamson, C.L., Zurko, M.E., Patel-Schneider, P.F., Shenoy, P.J. (eds.) Proceedings of the 16th International Conference on World Wide Web, WWW 2007, Banff, Alberta, Canada, May 8-12, 2007, pp. 657–666

Download references

Acknowledgements

This work is supported by the National Natural Science Foundation of China (No. 61902289), the Natural Science Foundation of Fujian Province (No. 2023J01534, No. 2023J01323), and the University-Industry Cooperation Project of Fujian Provincial Department of Science and Technology (No. 2022H6025), Fujian Special Financial Project for Reseach (No. 22SCZZX009), and the Start-up funds for scientific research of highlevel talents, Fujian Medical University (No. XRCZX2022010).

Author information

Authors and Affiliations

  1. The College of Computer and Cyber Security, Fujian Normal University, and also with Fujian Provincial Key Laboratory of Network Security and Cryptology, Fuzhou, 350000, Fujian, China

    Chengling Wang & Yuexin Zhang

  2. The School of Health, Fujian Medical University and also with Fujian Provincial Collaborative Innovation Center of Geriatric Rehabilitation and Industry Promotion, Fuzhou, 350108, Fujian, China

    Yunru Ma

  3. The Department of Orthopaedics, First Affiliated Hospital of Fujian Medical University, Fuzhou, 350108, Fujian, China

    Peng Chen

  4. Swinburne University of Technology, Melbourne, Australia

    Yang Xiang

Authors
  1. Chengling Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yuexin Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yunru Ma
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Peng Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Yang Xiang
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Wang Chengling was contributed conceptualization, methodology, validation and writing–original draft. Zhang Yuexin was involved in supervision, methodology and writing–review and editing. Ma Yunru was performed conceptualization and writing–review and editing. Chen Peng was done methodology. Yang Xiang did methodology and validation.

Corresponding author

Correspondence to Yuexin Zhang.

Ethics declarations

Conflict of interest

The authors declare no conflict of 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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, C., Zhang, Y., Ma, Y. et al. CNN-based continuous authentication for digital therapeutics using variational autoencoder. J Supercomput 81, 5 (2025). https://doi.org/10.1007/s11227-024-06490-2

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-024-06490-2

Keywords