Yantao Li
Hailong Hu
Gang Zhou
Skip Abstract Section
Abstract
Continuous authentication monitors the security of a system throughout the login session on mobile devices. In this article, we present SCANet, a two-stream convolutional neural network--based continuous authentication system that leverages the accelerometer and gyroscope on smartphones to monitor users’ behavioral patterns. We are among the first to use two streams of data—frequency domain data and temporal difference domain data—from the two sensors as the inputs of the convolutional neural network (CNN). SCANet utilizes the two-stream CNN to learn and extract representative features and then performs the principal component analysis to select the top 25 features with high discriminability. With the CNN-extracted features, SCANet exploits the one-class support vector machine to train the classifier in the enrollment phase. Based on the trained CNN and classifier, SCANet identifies the current user as a legitimate user or an impostor in the continuous authentication phase. We evaluate the effectiveness of the two-stream CNN and the performance of SCANet on our dataset and BrainRun dataset, and the experimental results demonstrate that CNN achieves 90.04% accuracy, and SCANet reaches an average of 5.14% equal error rate on two datasets and takes approximately 3 s for user authentication.
- Arsalan Mosenia, Susmita Sur-Kolay, Anand Reghunathan, and Niraj K. Jha. 2017. CABA: Continuous authentication based on BioAura. IEEE Trans. Comput. 66, 5 (2017), 759--772.Google Scholar
Digital Library
- Pin Shen Teh, Andrew Beng Jin Teoh, and Shigang Yue. 2013. A survey of keystroke dynamics biometrics. Sci. World J. (2013), Article ID 408280, 24 pages.Google Scholar
- Koichiro Niinuma, Unsang Park, and Anil K. Jain. 2010. Soft biometric traits for continuous user authentication. IEEE Trans. Inf. Forens. Secur. 5, 4 (2010), 771--780.Google ScholarDigital Library
- C. Sanchez-Avila and R. Sanchez-Reillo. 2005. Two different approaches for iris recognition using gabor filters and multiscale zero-crossing representation. Pattern Recogn. 38, 2 (2005), 231--240.Google ScholarCross Ref
- Lin Hong and Anil Jain. 1998. Integrating faces and fingerprints for personal identification. IEEE Trans. Pattern Anal. Mach. Intell. 20, 12 (1998), 1295--1307.Google ScholarDigital Library
- Ivan Martinovic, Kasper Rasmussen, Marc Roeschlin, and Gene Tsudik. 2017. Authentication using pulse-response biometrics. Commun. ACM 60, 2 (2017), 108--115.Google ScholarDigital Library
- Frederic Bimbot, Jean-Francois Bonastre, Corinne Fredouille, et. al. 2004. A tutorial on text-independent speaker verification. EURASIP J. Adv. Sign. Process. 2004, 4 (2004), 430--451.Google ScholarDigital Library
- Huan Feng, Kassem Fawaz, and Kang G. Shin. 2017. Continuous authentication for voice assistants. In Proceedings of the 23rd ACM/IEEE International Conference on Mobile Computing and Networking (MobiCom’17). ACM/IEEE, 343--355.Google Scholar
- Shanxun Chen, Amit Pande, and Prasant Mohapatra. 2014. Sensor-assisted facial recognition: An enhanced biometric authentication system for smartphones. In Proceedings of the 12th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys’14). ACM, 109--122.Google ScholarDigital Library
- Manuele Bicego, Andrea Lagorio, Enrico Grosso, and Massimo Tistarelli. 2006. On the use of sift features for face authentication. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW’06). IEEE, 1--7.Google ScholarDigital Library
- Cheng Bo, Lan Zhang, Taeho Jung, Junze Han, Xiang-Yang Li, and Yu Wang. 2014. Continuous user identification via touch and movement behavioral biometrics. In Proceedings of IEEE 33rd International Performance Computing and Communications Conference (IPCCC’14). IEEE, 1--8.Google ScholarCross Ref
- Bin Zou and Yantao Li. 2018. Touch-based smartphone authentication using import vector domain description. In Proceedings of the 29th IEEE International Conference on Application-specific Systems, Architectures and Processors (ASAP’18). IEEE, 85--88.Google ScholarCross Ref
- J. Mantyjarvi, M. Lindholm, E. Vildjiounaite, S.-M. Makela, and H. Ailisto. 2005. Identifying users of portable devices from gait pattern with accelerometers. In Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP’05). IEEE, II973-II976.Google Scholar
- Yantao Li, Hailong Hu, Gang Zhou, and Shaojiang Deng. 2018. Sensor-based continuous authentication using cost-effective kernel ridge regression. IEEE Access 6, 5 (2018), 32554--32565.Google ScholarCross Ref
- Senaka Buthpitiya, Ying Zhang, Anind K. Dey, and Martin Griss. 2011. n-gram geo-trace modeling. In Proceedings of the International Conference on Pervasive Computing, Lecture Notes in Computer Science. 97--114.Google Scholar
- Ge Peng, Gang Zhou, David T. Nguyen, Xin Qi, Qing Yang, and Shuangquan Wang. 2017. Continuous authentication with touch behavioral biometrics and voice on wearable glasses. IEEE Trans. Hum.-Mach. Syst. 47, 3 (2017), 404--416.Google ScholarCross Ref
- Mario Parreño Centeno, Yu Guan, and Ada van Moorsel. 2018. Mobile based continuous authentication using deep features. In Proceedings of the 2nd International Workshop on Embedded and Mobile Deep Learning (EMDL’18). IEEE, 19--24.Google ScholarDigital Library
- Mario Parreño Centeno, Ada van Moorsel and Stefano Castruccio. 2017. Smartphone continuous authentication using deep learning autoencoders. In Proceedings of 15th Annual Conference on Privacy, Security and Trust (PST’17). IEEE, 147--155.Google ScholarCross Ref
- Chris Xiaoxuan Lu, Bowen Du, Peijun Zhao, Hongkai Wen, Yiran Shen, Andrew Markham, and Niki Trigoni. 2018. DeepAuth: In-situ authentication for smartwatches via deeply learned behavioural biometrics. In Proceedings of the International Symposium on Wearable Computers (ISWC’18). ACM, 204--207.Google ScholarDigital Library
- Upal Mahbub, Vishal M. Patel, Deepak Chandra, Brandon Barbello, and Rama Chellappa. 2016. Partial face detection for continuous authentication. In Proceedings of the IEEE International Conference on Image Processing (ICIP’16). IEEE, 2991--2995.Google ScholarCross Ref
- A. Hadid, J. Y. Heikkila, O. Silven, and M. Pietikainen. 2007. Face and eye detection for person authentication in mobile phones. In Proceedings of the ACM/IEEE International Conference on Distributed Smart Cameras. ACM/IEEE, 101--108.Google Scholar
- Aditi Roy, Tzipora Halevi, and Nasir Memon. 2015. An HMM-based multi-sensor approach for continuous mobile authentication. In Proceedings of the 2015 IEEE Military Communications Conference (MILCOM’15). 1311--1316.Google ScholarCross Ref
- Zden̆ka Sitová, Jaroslav S̆edĕnka, Qing Yang, Ge Peng, Gang Zhou, Paolo Gasti, and Kiran S. Balagani. 2016. Hmog: New behavioral biometric features for continuous authentication of smartphone users. IEEE Trans. Inf. Forens. Secur. 11, 5 (2016), 877--892.Google ScholarDigital Library
- Nabilah Shabrina, Tsuyoshi Isshiki, and Hiroaki Kunieda. 2016. Fingerprint authentication on touch sensor using phase-only correlation method. In Proceedings of the 7th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES’16). IEEE, 85--89.Google ScholarCross Ref
- Chao Shen, Yuanxun Li, Yufei Chen, Xiaohong Guan, and Roy A. Maxion. 2018. Performance analysis of multi-motion sensor behavior for active smartphone authentication. IEEE Trans. Inf. Forens. Secur. 13, 1 (2018), 48--62.Google ScholarCross Ref
- Yantao Li, Hailong Hu, and Gang Zhou. 2019. Using data augmentation in continuous authentication on smartphones. IEEE IoT J. 6, 1 (2019), 628--640.Google Scholar
- Oren Rippel, Jasper Snoek, and Ryan P. Adams. 2015. Spectral representations for convolutional neural networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS’15). ACM, 2449--2457.Google Scholar
- Tao Feng, Jun Yang, Zhixian Yan, Emmauenl M. Tapia, and Weidong Shi. 2014. Tips: Contextaware implicit user identification using touch screen in uncontrolled environments. In Proceedings of the 15th International Workshop on Mobile Computing Systems and Applications (HotMobile’14). ACM, 1--6, 2014.Google ScholarDigital Library
- Hailong Hu, Yantao Li, Zhangqian Zhu, and Gang Zhou. 2018. CNNAuth: Continuous authentication via two-stream convolutional neural networks. In Proceedings of 2018 IEEE 13th International Conference on Networking, Architecture and Storage (NAS’18). IEEE, 1--9.Google ScholarCross Ref
- Tim Cooijmans, Nicolas Ballas, Cesar Laurent, caglar Gulcehre and Aaron Courville. 2017. Recurrent batch normalization. In Proceedings of the 5th International Conference on Learning Representations (ICLR’17). 1--13.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). IEEE, 770--778.Google ScholarCross Ref
- Young-Jin Cha, Wooram Choi, Gahyun Suh, Sadegh Mahmoudkhani, and Oral Büyüköztürk. 2018. Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput.-Aid. Civil Infrastr. Eng. 33, 9 (2018), 731--747.Google ScholarDigital Library
- Young-Jin Cha, Wooram Choi, and Oral Büyüköztürk. 2017. Deep learning-based crack damage detectionu sing convolutional neural networks. Comput.-Aid. Civil Infrastr. Eng. 32, 5 (2017) 361--378.Google ScholarDigital Library
- Alex Krizhevsky, Ilya Sutskever, and Geofrey E. Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS’12). ACM, 1097--1105.Google ScholarDigital Library
- Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of International Conference on Learning Representations (ICLR’15). 1--14.Google Scholar
- Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv Preprint arXiv:1704.04861 (2017).Google Scholar
- Xiangyu Zhang, Xinyu Zhou, Mengxiao Lin, and Jian Sun. 2017. ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’18). IEEE, 6848--6856.Google Scholar
- Mark Sandler, Andrew Howard, Menglong Zhu, Andrey Zhmoginov, and Liang-Chieh Chen. 2018. Inverted residuals and linear bottlenecks: Mobile networks for classification, detection and segmentation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR’18). IEEE, 4510--4520.Google Scholar
- Karen Simonyan and Andrew Zisserman. 2014. Two-stream convolutional networks for action recognition in videos. In Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS’14). ACM, 568--576.Google Scholar
- Laurent Slfre and Stephane Mallat. 2014. Rigid-motion scattering for texture classification. Int. J. Comput. Vis. 107, 2 (2014), 501--515.Google Scholar
- Francois Chollet. 2017. Xception: Deep learning with depthwise separable convolutions. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR’17). IEEE, 1800--1807.Google ScholarCross Ref
- Lingjun Li, Xinxin Zhao, and Guoliang Xue. 2013. Unobservable re-authentication for smartphones. In Proceedings of the 20th Annual Network and Distributed System Security Symposium (NDSS’13). 1--16.Google Scholar
- Cheng Bo, Lan Zhang, Xiang-Yang Li, Qiuyuan Huang, and Yu Wang. 2013. SilentSense: Silent user identification via touch and movement behavioral biometrics. In Proceedings of the 19th Annual International Conference on Mobile Computing and Networking (MobiCom’13). ACM, 187--190.Google ScholarDigital Library
- Larry M. Manevitz and Malik Yousef. 2002. One-class svms for document classification. J. Mach. Learn. Res. 2, 2 (2002), 139--154.Google ScholarDigital Library
- Yantao Li, Bin Zou, Shaojiang Deng, and Gang Zhou. 2020. Using feature fusion strategies in continuous authentication on smartphones. IEEE Internet Comput. 24, 2 (2020), 49--56.Google ScholarCross Ref
- Wei-Han Lee and Ruby Lee. 2016. Implicit sensor-based authentication of smartphone users with smartwatch. In Proceedings of the Hardware and Architectural Support for Security and Privacy (HASP’16). 1--8.Google ScholarDigital Library
- Senaka Buthpitiya, Ying Zhang, Anind K. Dey, and Martin L. Griss. 2011. n-gram geo-trace modeling. In Proceedings of International Conference on Pervasive Computing (ICPC’11). IEEE, 97--114.Google Scholar
- Shuochao Yao, Shaohan Hu, Yiran Zhao, Aston Zhang, and Tarek Abdelzaher. 2017. Deepsense: A unified deep learning framework for time-series mobile sensing data processing. In Proceedings of the 26th International Conference on World Wide Web (WWW’17). 351--360.Google ScholarDigital Library
- Matteo Gadaleta and Michele Rossi. 2018. IDNet: Smartphone-based gait recognition with convolutional neural networks. Pattern Recogn. 74, 2 (2018), 25--37.Google ScholarDigital Library
- Chao Shen, Tianwen Yu, Sheng Yuan, Yunpeng Li, and Xiaohong Guan. 2016. Performance analysis of motion-sensor behavior for user authentication on smartphones. Sensors 16, 3 (2016), 345:1--21.Google Scholar
- Leif E. Peterson. 2009. K-nearest neighbor. Scholarpedia 4, 2 (2009), 1883.Google ScholarCross Ref
- Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference for Learning Representations (ICLR’15). 1--15.Google Scholar
- Alexander Senf, Xue-wen Chen, and Anne Zhang. 2006. Comparison of one-class SVM and two-class SVM for fold recognition. In Proceedings of 2006 International Conference on Neural Information Processing (ICONIP’06). Lecture Notes in Computer Science, 140--149.Google ScholarDigital Library
- Pei-Yuan Wu, Chi-Chen Fang, Jien Morris Chang, and Sun-Yuan Kung. 2016. Cost-effective kernel ridge regression implementation for keystroke-based active authentication system. IEEE Trans. Cybernet. 47, 11 (2017), 3916--3927.Google ScholarCross Ref
- Michail D. Papamichail, Kyriakos C. Chatzidimitriou, Thomas Karanikiotis, Napoleon-Christos I. Oikonomou, Andreas L. Symeonidis, and Sashi K. Saripalle. 2019. BrainRun: A behavioral biometrics dataset towards continuous implicit authentication. Data 4, 2 (2019), 1--17.Google ScholarCross Ref
Index Terms
- SCANet: Sensor-based Continuous Authentication with Two-stream Convolutional Neural Networks
Recommendations
Mobile Based Continuous Authentication Using Deep Features
EMDL'18: Proceedings of the 2nd International Workshop on Embedded and Mobile Deep LearningContinuous authentication is a promising approach to validate the user's identity during a work session, e.g., for mobile banking applications. Recently, it has been demonstrated that changes in the motion patterns of the user may help to note the ...
AuthConFormer: Sensor-based Continuous Authentication of Smartphone Users Using A Convolutional Transformer
AbstractTo prevent the leakage of personal information on smartphones, a method that can authenticate the smartphone user’s identity throughout the session is essential. Sensor-based continuous authentication is a promising potential approach that uses ...
Pulse-Response: Exploring Human Body Impedance for Biometric Recognition
Biometric characteristics are often used as a supplementary component in user authentication and identification schemes. Many biometric traits, both physiological and behavioral, offering a wider range of security and stability, have been explored. We ...
Comments