Improving the Security of Smartwatch Payment with Deep Learning (2307.05437v1)
Abstract: Making contactless payments using a smartwatch is increasingly popular, but this payment medium lacks traditional biometric security measures such as facial or fingerprint recognition. In 2022, Sturgess et al. proposed WatchAuth, a system for authenticating smartwatch payments using the physical gesture of reaching towards a payment terminal. While effective, the system requires the user to undergo a burdensome enrolment period to achieve acceptable error levels. In this dissertation, we explore whether applications of deep learning can reduce the number of gestures a user must provide to enrol into an authentication system for smartwatch payment. We firstly construct a deep-learned authentication system that outperforms the current state-of-the-art, including in a scenario where the target user has provided a limited number of gestures. We then develop a regularised autoencoder model for generating synthetic user-specific gestures. We show that using these gestures in training improves classification ability for an authentication system. Through this technique we can reduce the number of gestures required to enrol a user into a WatchAuth-like system without negatively impacting its error rates.
- “Paying with Your Wrist: The Future of Wearable Payments” In Financial and Business News | Finance Magnates, https://www.financemagnates.com/fintech/payments/paying-with-your-wrist-the-future-of-wearable-payments/, 2023
- “WatchAuth: User Authentication and Intent Recognition in Mobile Payments Using a Smartwatch” In 2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P) Los Alamitos, CA, USA: IEEE Computer Society, 2022, pp. 377–391 DOI: 10.1109/EuroSP53844.2022.00031
- “Continuous Authentication on a Smartwatch” In Proceedings of the International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2022), Lecture Notes in Networks and Systems Cham: Springer International Publishing, 2022, pp. 1007–1018 DOI: 10.1007/978-3-031-21333-5_101
- “WACA: Wearable-Assisted Continuous Authentication” In 2018 IEEE Security and Privacy Workshops (SPW), 2018, pp. 264–269 DOI: 10.1109/SPW.2018.00042
- Neamah Hasan Al-Naffakh “Activity-Based User Authentication Using Smartwatches”, 2020
- Andrew H. Johnston and Gary M. Weiss “Smartwatch-Based Biometric Gait Recognition” In 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems (BTAS), 2015, pp. 1–6 DOI: 10.1109/BTAS.2015.7358794
- Junshuang Yang, Yanyan Li and Mengjun Xie “MotionAuth: Motion-based Authentication for Wrist Worn Smart Devices” In 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops), 2015, pp. 550–555 DOI: 10.1109/PERCOMW.2015.7134097
- Guan-Cheng Liang, Xiang-Yu Xu and Jia-Di Yu “User-Authentication on Wearable Devices Based on Punch Gesture Biometrics” In ITM Web of Conferences 11, 2017, pp. 01003 DOI: 10.1051/itmconf/20171101003
- “User Authentication Using Wrist Mounted Inertial Sensors: Poster Abstract” In Proceedings of the 16th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN ’17 New York, NY, USA: Association for Computing Machinery, 2017, pp. 309–310 DOI: 10.1145/3055031.3055063
- Sunwoo Lee, Wonsuk Choi and Dong Hoon Lee “Usable User Authentication on a Smartwatch Using Vibration” In Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, CCS ’21 New York, NY, USA: Association for Computing Machinery, 2021, pp. 304–319 DOI: 10.1145/3460120.3484553
- “Smartwatch User Authentication by Sensing Tapping Rhythms and Using One-Class DBSCAN” In Sensors 21.7 Multidisciplinary Digital Publishing Institute, 2021, pp. 2456 DOI: 10.3390/s21072456
- “TrueHeart: Continuous Authentication on Wrist-worn Wearables Using PPG-based Biometrics” In IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Toronto, ON, Canada: IEEE, 2020, pp. 30–39 DOI: 10.1109/INFOCOM41043.2020.9155526
- “Learning Human Identity From Motion Patterns” In IEEE Access 4, 2016, pp. 1810–1820 DOI: 10.1109/ACCESS.2016.2557846
- “Deep Learning Approaches for Continuous Authentication Based on Activity Patterns Using Mobile Sensing” In Sensors 21.22 Multidisciplinary Digital Publishing Institute, 2021, pp. 7519 DOI: 10.3390/s21227519
- “Multisensor-Based Continuous Authentication of Smartphone Users With Two-Stage Feature Extraction” In IEEE Internet of Things Journal 10.6, 2023, pp. 4708–4724 DOI: 10.1109/JIOT.2022.3219135
- “CNN-Based Continuous Authentication on Smartphones With Conditional Wasserstein Generative Adversarial Network” In IEEE Internet of Things Journal 9.7, 2022, pp. 5447–5460 DOI: 10.1109/JIOT.2021.3108822
- “Deepauth: In-Situ Authentication for Smartwatches via Deeply Learned Behavioural Biometrics” In Proceedings of the 2018 ACM International Symposium on Wearable Computers, ISWC ’18 New York, NY, USA: Association for Computing Machinery, 2018, pp. 204–207 DOI: 10.1145/3267242.3267252
- “Deep Residual Network for Smartwatch-Based User Identification through Complex Hand Movements” In Sensors 22, 2022, pp. 3094 DOI: 10.3390/s22083094
- “ThumbUp: Identification and Authentication by Smartwatch Using Simple Hand Gestures” In 2020 IEEE International Conference on Pervasive Computing and Communications (PerCom), 2020, pp. 1–10 DOI: 10.1109/PerCom45495.2020.9127367
- “Data Augmentation of Wearable Sensor Data for Parkinson’s Disease Monitoring Using Convolutional Neural Networks” In Proceedings of the 19th ACM International Conference on Multimodal Interaction, 2017, pp. 216–220 DOI: 10.1145/3136755.3136817
- “Data Augmentation Techniques in Time Series Domain: A Survey and Taxonomy” In Neural Computing and Applications 35.14, 2023, pp. 10123–10145 DOI: 10.1007/s00521-023-08459-3
- “Enhancing Human Activity Recognition Using Deep Learning and Time Series Augmented Data” In Journal of Ambient Intelligence and Humanized Computing 12.12, 2021, pp. 10565–10580 DOI: 10.1007/s12652-020-02865-4
- “Using Variational Autoencoder to Augment Sparse Time Series Datasets” In 2021 7th International Conference on Optimization and Applications (ICOA), 2021, pp. 1–6 DOI: 10.1109/ICOA51614.2021.9442619
- Jack Sturgess “WatchAuth Dataset (Extended)”, University of Oxford, 2023
- “On the Properties of Neural Machine Translation: Encoder–Decoder Approaches” In Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation Doha, Qatar: Association for Computational Linguistics, 2014, pp. 103–111 DOI: 10.3115/v1/W14-4012
- Joseph Rocca “Understanding Variational Autoencoders (VAEs)” In Medium, https://towardsdatascience.com/understanding-variational-autoencoders-vaes-f70510919f73, 2021
- “Wasserstein Auto-Encoders” In International Conference on Learning Representations, 2018
- Diederik P. Kingma and Max Welling “Auto-Encoding Variational Bayes” In 2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings, 2014
- “Dynamic Programming Algorithm Optimization for Spoken Word Recognition” In Readings in Speech Recognition San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 1990, pp. 159–165
- Geoffrey I. Webb and Francois Petitjean “Tight Lower Bounds for Dynamic Time Warping” In Pattern Recognition 115, 2021, pp. 107895 DOI: 10.1016/j.patcog.2021.107895
- “Evaluating Behavioral Biometrics for Continuous Authentication: Challenges and Metrics” In Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security Abu Dhabi United Arab Emirates: ACM, 2017, pp. 386–399 DOI: 10.1145/3052973.3053032
- Subhrajit Roy, Isabell Kiral-Kornek and Stefan Harrer “ChronoNet: A Deep Recurrent Neural Network for Abnormal EEG Identification” In Artificial Intelligence in Medicine 11526 Cham: Springer International Publishing, 2019, pp. 47–56 DOI: 10.1007/978-3-030-21642-9_8
- Geoffrey Hinton, Oriol Vinyals and Jeff Dean “Distilling the Knowledge in a Neural Network” arXiv, 2015 arXiv:arXiv:1503.02531
- Cezara Benegui and Radu Tudor Ionescu “To Augment or Not to Augment? Data Augmentation in User Identification Based on Motion Sensors” In Neural Information Processing: 27th International Conference, ICONIP 2020, Bangkok, Thailand, November 18–22, 2020, Proceedings, Part V 27 Springer, 2020, pp. 822–831
- “Soft-DTW: A Differentiable Loss Function for Time-Series” In Proceedings of the 34th International Conference on Machine Learning PMLR, 2017, pp. 894–903
- Mehran Maghoumi, Eugene Matthew Taranta and Joseph LaViola “DeepNAG: Deep Non-Adversarial Gesture Generation” In 26th International Conference on Intelligent User Interfaces, IUI ’21 New York, NY, USA: Association for Computing Machinery, 2021, pp. 213–223 DOI: 10.1145/3397481.3450675
- “Developing a Pattern Discovery Method in Time Series Data and Its GPU Acceleration” In Big Data Mining and Analytics 1.4, 2018, pp. 266–283 DOI: 10.26599/BDMA.2018.9020021
- “TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems”, https://www.tensorflow.org/, 2015
- “PyTorch: An Imperative Style, High-Performance Deep Learning Library” In Advances in Neural Information Processing Systems 32 Curran Associates, Inc., 2019, pp. 8024–8035
- Tao Qin, Tie-Yan Liu and Hang Li “A General Approximation Framework for Direct Optimization of Information Retrieval Measures” In Information Retrieval 13.4, 2010, pp. 375–397 DOI: 10.1007/s10791-009-9124-x
- “TF-Ranking: Scalable TensorFlow Library for Learning-to-Rank” In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2019, pp. 2970–2978
- “Data Augmentation with Variational Autoencoders and Manifold Sampling” In Deep Generative Models, and Data Augmentation, Labelling, and Imperfections Cham: Springer International Publishing, 2021, pp. 184–192
- “Zero-VAE-GAN: Generating Unseen Features for Generalized and Transductive Zero-Shot Learning” In IEEE Transactions on Image Processing 29, 2020, pp. 3665–3680 DOI: 10.1109/TIP.2020.2964429