Few-Shot Continuous Authentication for Mobile-Based Biometrics
The rapid growth of smartphone financial services raises the need for secure mobile authentication. Continuous authentication is a user-friendly way to strengthen the security of smartphones by implicitly monitoring a user’s identity through sessions. Mobile continuous authentication can be viewed a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/20/10365 |
| _version_ | 1797475615815761920 |
|---|---|
| author | Kensuke Wagata Andrew Beng Jin Teoh |
| author_facet | Kensuke Wagata Andrew Beng Jin Teoh |
| author_sort | Kensuke Wagata |
| collection | DOAJ |
| description | The rapid growth of smartphone financial services raises the need for secure mobile authentication. Continuous authentication is a user-friendly way to strengthen the security of smartphones by implicitly monitoring a user’s identity through sessions. Mobile continuous authentication can be viewed as an anomaly detection problem in which models discriminate between one genuine user and the rest of the impostors (anomalies). In practice, complete impostor profiles are hardly available due to the time and monetary cost, while leveraging genuine data alone yields poorly generalized models due to the lack of knowledge about impostors. To address this challenge, we recast continuous mobile authentication as a few-shot anomaly detection problem, aiming to enhance the inference robustness of unseen impostors by using partial knowledge of available impostor profiles. Specifically, we propose a novel deep learning-based model, namely a local feature pooling-based temporal convolution network (LFP-TCN), which directly models raw sequential mobile data, aggregating global and local feature information. In addition, we introduce a random pattern mixing augmentation to generate class-unconstrained impostor data for the training. The augmented pool enables characterizing various impostor patterns from limited impostor data. Finally, we demonstrate practical continuous authentication using score-level fusion, which prevents long-term dependency or increased model complexity due to extended re-authentication time. Experiments on two public benchmark datasets show the effectiveness of our method and its state-of-the-art performance. |
| first_indexed | 2024-03-09T20:46:41Z |
| format | Article |
| id | doaj.art-6c7ed6823b8e4fd89d99ac8d4fa66502 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T20:46:41Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-6c7ed6823b8e4fd89d99ac8d4fa665022023-11-23T22:43:23ZengMDPI AGApplied Sciences2076-34172022-10-0112201036510.3390/app122010365Few-Shot Continuous Authentication for Mobile-Based BiometricsKensuke Wagata0Andrew Beng Jin Teoh1School of Electrical and Electronic Engineering, College of Engineering, Yonsei University, Seoul 03722, KoreaSchool of Electrical and Electronic Engineering, College of Engineering, Yonsei University, Seoul 03722, KoreaThe rapid growth of smartphone financial services raises the need for secure mobile authentication. Continuous authentication is a user-friendly way to strengthen the security of smartphones by implicitly monitoring a user’s identity through sessions. Mobile continuous authentication can be viewed as an anomaly detection problem in which models discriminate between one genuine user and the rest of the impostors (anomalies). In practice, complete impostor profiles are hardly available due to the time and monetary cost, while leveraging genuine data alone yields poorly generalized models due to the lack of knowledge about impostors. To address this challenge, we recast continuous mobile authentication as a few-shot anomaly detection problem, aiming to enhance the inference robustness of unseen impostors by using partial knowledge of available impostor profiles. Specifically, we propose a novel deep learning-based model, namely a local feature pooling-based temporal convolution network (LFP-TCN), which directly models raw sequential mobile data, aggregating global and local feature information. In addition, we introduce a random pattern mixing augmentation to generate class-unconstrained impostor data for the training. The augmented pool enables characterizing various impostor patterns from limited impostor data. Finally, we demonstrate practical continuous authentication using score-level fusion, which prevents long-term dependency or increased model complexity due to extended re-authentication time. Experiments on two public benchmark datasets show the effectiveness of our method and its state-of-the-art performance.https://www.mdpi.com/2076-3417/12/20/10365continuous authenticationtouch-gesture biometricsfew-shot anomaly detectiondata augmentationtemporal convolution network |
| spellingShingle | Kensuke Wagata Andrew Beng Jin Teoh Few-Shot Continuous Authentication for Mobile-Based Biometrics Applied Sciences continuous authentication touch-gesture biometrics few-shot anomaly detection data augmentation temporal convolution network |
| title | Few-Shot Continuous Authentication for Mobile-Based Biometrics |
| title_full | Few-Shot Continuous Authentication for Mobile-Based Biometrics |
| title_fullStr | Few-Shot Continuous Authentication for Mobile-Based Biometrics |
| title_full_unstemmed | Few-Shot Continuous Authentication for Mobile-Based Biometrics |
| title_short | Few-Shot Continuous Authentication for Mobile-Based Biometrics |
| title_sort | few shot continuous authentication for mobile based biometrics |
| topic | continuous authentication touch-gesture biometrics few-shot anomaly detection data augmentation temporal convolution network |
| url | https://www.mdpi.com/2076-3417/12/20/10365 |
| work_keys_str_mv | AT kensukewagata fewshotcontinuousauthenticationformobilebasedbiometrics AT andrewbengjinteoh fewshotcontinuousauthenticationformobilebasedbiometrics |