Abstract
The connectivity of smart technologies, such as smartphones and smart wearables, is ever-increasing with the emergence of the internet of things (IoT). This technological advancement makes it possible to serve emerging applications, such as financial transactions, healthcare check-ups, and property access, easily through smart wearables, such as Apple Watch. This also presents a new vulnerability as hackers have more opportunities to attack users via the wearables. As the current knowledge-based wearable authentication schemes, such as passwords, PINs, or pattern locks, are overwhelming for users, we need an authentication system that can validate a user implicitly, i.e., without the need for active user interaction. In this work, we present an authentication system for the wearables leveraging the sensing and computation power of smartphones and IoT connectivity. We develop a smartphone application (TFL Auth app) using the TensorFlow Lite framework and an on-phone convolutional neural network (CNN) model that listens to a user’s breathing patterns through the microphone and verifies the user’s identity in real-time before sending the acceptance/rejection notification to a paired wearable that we want to secure. From a detailed analysis, we are able to achieve an average accuracy of 0.92 ± 0.01 using the Mel-frequency cepstral coefficients.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Forecasted value of the global wearable devices market. https://goo.gl/C682Rv (2018). Accessed February 2018
Esc-50: Dataset for environmental sound classification. https://bit.ly/2uT9Ddc (2019). Accessed November 2019
Chaquopy python SDK for android. https://chaquo.com/chaquopy/ (2020). Accessed June 2020
Dropout on CNN vs. RNN. https://rb.gy/ki1iwx (2020). Accessed October 2020
Google cloud compute engine. https://cloud.google.com/compute (2020). Accessed June 2020
How to talk to phone apps. https://rb.gy/7ih2ow (2020). Accessed July 2020
Implementing websockets to communicate between fitbit versa and local server! https://rb.gy/usg8oo (2020). Accessed July 2020
Internet. https://ourworldindata.org/internet. Accessed October 2020
McAfee research finds troubling use of insecure cloud passwords. https://rb.gy/7fnde8 (2020). Accessed: June 2020
spafe: Simplified python audio-features extraction. https://rb.gy/jmdvms (2020). Accessed June 2020
Tensorflow lite example apps. https://rb.gy/ggnlz3 (2020). Accessed June 2020
Urbansound8k dataset. Available: https://bit.ly/2uHhhYh (2020). Accessed March 2020
Acar, A., Aksu, H., Uluagac, A.S., et al.: Waca: Wearable-assisted continuous authentication (2018). Preprint arXiv:1802.10417
Al Amin, M.T., Barua, S., Vhaduri, S., Rahman, A.: Load aware broadcast in mobile ad hoc networks. In: 2009 IEEE International Conference on Communications, pp. 1–5. IEEE, Piscataway (2009)
Bugdol, M.D., Mitas, A.W.: Multimodal biometric system combining ecg and sound signals. Patt. Recog. Lett. 38, 107–112 (2014)
Camlikaya, E., Kholmatov, A., Yanikoglu, B.: Multi-biometric templates using fingerprint and voice. In: Biometric Technology for Human Identification V, vol. 6944, p. 69440I. International Society for Optics and Photonics, Bellingham (2008)
Chauhan, J., Hu, Y., Seneviratne, S., et al.: Breathprint: Breathing acoustics-based user authentication. In: ACM Mobile Systems, Applications, and Services (2017)
Chauhan, J., Seneviratne, S., Hu, Y., et al.: Breathing-based authentication on resource-constrained IoT devices using recurrent neural networks. Computer 51(5), 60–67 (2018)
Chen, C.Y., Vhaduri, S., Poellabauer, C.: Estimating sleep duration from temporal factors, daily activities, and smartphone use. In: 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), pp. 545–554. IEEE, Piscataway (2020)
Cheung, W., Vhaduri, S.: Context-dependent implicit authentication for wearable device users. In: IEEE Personal, Indoor and Mobile Radio Communications (PIMRC) (2020)
Cheung, W., Vhaduri, S.: Continuous authentication of wearable device users from heart rate, gait, and breathing data. In: IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) (2020)
Cola, G., Avvenuti, M., Musso, F., et al.: Gait-based authentication using a wrist-worn device. In: ACM Mobile and Ubiquitous Systems: Computing, Networking and Services (2016)
Dai, H., Wang, W., Liu, A.X., et al.: Speech based human authentication on smartphones. In: IEEE International Conference on Sensing, Communication, and Networking (SECON) (2019)
Kim, Y., Vhaduri, S., Poellabauer, C.: Understanding college students’ phone call behaviors towards a sustainable mobile health and wellbeing solution. In: International Conference on Systems Engineering (CIIS) (2020)
Kumar, R., Phoha, V.V., Raina, R.: Authenticating users through their arm movement patterns (2016). Preprint arXiv:1603.02211
Lalitha, S., Tripathi, S., Gupta, D.: Enhanced speech emotion detection using deep neural networks. Int. J. Speech Technol. 22(3), 497–510 (2019)
Liu, J., Dong, Y., Chen, Y., et al.: Leveraging breathing for continuous user authentication. In: International Conference on Mobile Computing and Networking (2018)
McFee, B., Raffel, C., Liang, et al.: librosa: Audio and music signal analysis in python. In: Python in Science Conference (2015)
Mohsin, A., Zaidan, A., Zaidan, B., Albahri, O., Ariffin, S.A.B., Alemran, A., Enaizan, O., Shareef, A.H., Jasim, A.N., Jalood, N., et al.: Finger vein biometrics: taxonomy analysis, open challenges, future directions, and recommended solution for decentralised network architectures. IEEE Access 8, 9821–9845 (2020)
Muratyan, A., Cheung, W., Dibbo, S.V., Vhaduri, S.: Opportunistic multi-modal user authentication for health-tracking iot wearables. In: the 5th EAI International Conference on Safety and Security with IoT (SaSeIoT) (2021)
Sarkar, A., Abbott, A.L., Doerzaph, Z.: Biometric authentication using photoplethysmography signals. In: Biometrics Theory, Applications and Systems (BTAS). IEEE, Piscataway (2016)
Sun, F., Mao, C., Fan, X., et al.: Accelerometer-based speed-adaptive gait authentication method for wearable iot devices. IEEE Int. Things J. 6(1), 820–830 (2018)
Vhaduri, S.: Nocturnal cough and snore detection using smartphones in presence of multiple background-noises. In: Proceedings of the 3rd ACM SIGCAS Conference on Computing and Sustainable Societies, pp. 174–186 (2020)
Vhaduri, S., Ali, A., Sharmin, M., Hovsepian, K., Kumar, S.: Estimating drivers’ stress from GPS traces. In: Proceedings of the 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications, pp. 1–8 (2014)
Vhaduri, S., Brunschwiler, T.: Towards automatic cough and snore detection. In: 2019 IEEE International Conference on Healthcare Informatics (ICHI), pp. 1–1. IEEE, Piscataway (2019)
Vhaduri, S., Munch, A., Poellabauer, C.: Assessing health trends of college students using smartphones. In: 2016 IEEE Healthcare Innovation Point-Of-Care Technologies Conference (HI-POCT), pp. 70–73. IEEE, Piscataway (2016)
Vhaduri, S., Poellabauer, C.: Cooperative discovery of personal places from location traces. In: 25th International Conference on Computer Communication and Networks (ICCCN). IEEE, Piscataway (2016)
Vhaduri, S., Poellabauer, C.: Design and implementation of a remotely configurable and manageable well-being study. In: Smart City 360, pp. 179–191. Springer, Berlin (2016)
Vhaduri, S., Poellabauer, C.: Human factors in the design of longitudinal smartphone-based wellness surveys. In: 2016 IEEE International Conference on Healthcare Informatics (ICHI), pp. 156–167. IEEE, Piscataway (2016)
Vhaduri, S., Poellabauer, C.: Design factors of longitudinal smartphone-based health surveys. J. Healthcare Inf. Res. 1(1), 52–91 (2017)
Vhaduri, S., Poellabauer, C.: Hierarchical cooperative discovery of personal places from location traces. IEEE Trans. Mobile Comput. 17(8), 1865–1878 (2017)
Vhaduri, S., Poellabauer, C.: Towards reliable wearable-user identification. In: 2017 IEEE International Conference on Healthcare Informatics (ICHI). pp. 329–329. IEEE Computer Society, Washington (2017)
Vhaduri, S., Poellabauer, C.: Wearable device user authentication using physiological and behavioral metrics. In: IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC) (2017)
Vhaduri, S., Poellabauer, C.: Biometric-based wearable user authentication during sedentary and non-sedentary periods. In: International Workshop on Security and Privacy for the Internet-of-Things (2018)
Vhaduri, S., Poellabauer, C.: Impact of different pre-sleep phone use patterns on sleep quality. In: IEEE 15th International Conference on Wearable and Implantable Body Sensor Networks (BSN) (2018)
Vhaduri, S., Poellabauer, C.: Opportunistic discovery of personal places using multi-source sensor data. IEEE Transactions on Big Data 7(2), 383–396 (2018)
Vhaduri, S., Poellabauer, C.: Opportunistic discovery of personal places using smartphone and fitness tracker data. In: 2018 IEEE International Conference on Healthcare Informatics (ICHI), pp. 103–114. IEEE, Piscataway (2018)
Vhaduri, S., Poellabauer, C.: Multi-modal biometric-based implicit authentication of wearable device users. IEEE Trans. Inf. Foren. Secur. 14(12), 3116–3125 (2019)
Vhaduri, S., Poellabauer, C.: Summary: Multi-modal biometric-based implicit authentication of wearable device users (2019). Preprint arXiv:1907.06563
Vhaduri, S., Poellabauer, C., Striegel, A., Lizardo, O., Hachen, D.: Discovering places of interest using sensor data from smartphones and wearables. In: 2017 IEEE SmartWorld, Ubiquitous Intelligence & Computing (UIC) (2017)
Vhaduri, S., Prioleau, T.: Adherence to personal health devices: A case study in diabetes management. In: EAI International Conference on Pervasive Computing Technologies for Healthcare (EAI PervasiveHealth) (2020)
Vhaduri, S., Van Kessel, T., Ko, B., Wood, D., Wang, S., Brunschwiler, T.: Nocturnal cough and snore detection in noisy environments using smartphone-microphones. In: 2019 IEEE International Conference on Healthcare Informatics (ICHI), pp. 1–7. IEEE, Piscataway (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dibbo, S.V., Cheung, W., Vhaduri, S. (2023). On-Phone CNN Model-Based Implicit Authentication to Secure IoT Wearables. In: Nayyar, A., Paul, A., Tanwar, S. (eds) The Fifth International Conference on Safety and Security with IoT . EAI/Springer Innovations in Communication and Computing. Springer, Cham. https://doi.org/10.1007/978-3-030-94285-4_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-94285-4_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-94284-7
Online ISBN: 978-3-030-94285-4
eBook Packages: EngineeringEngineering (R0)