ABSTRACT
Continuous Implicit Authentication (CIA) provides a imperceptible and passive validation in a whole process of operating the mobile devices. In this paper, we describe users’ behavioral patterns through the build-in sensors of smartphones, and apply them to our authentication system. The current work is mainly implemented in a controlled experimental environment. We prove the effectiveness of the implicit authentication method in the natural environment through the analysis of only the touch screen process and the entire process of the user using the mobile phone. We focus on the multi-class strategy in CIA, in which a classifier has to recognize the “owner” of a series of operations from identity banks. To extract temporal domain and space domain features and enhance the classifier's discriminative power, our system utilizes Resnet with Squeeze-and-Excitation incorporating Attention blocks and Additive Angular Margin Loss. We evaluate our system both in our dataset and BrainRun dataset, and the accuracies of distinguish the correct identity achieves are 96.94% and 87.11% respectively. Specially, with the continuous data in BrainRun, the result is generated from behaviors during 5 s in a more interactive game.
- Aviv A J, Gibson K L, Mossop E, Smudge attacks on smartphone touch screens[J]. Woot, 2010, 10: 1-7.Google Scholar
- Wiedenbeck S, Waters J, Sobrado L, Design and evaluation of a shoulder-surfing resistant graphical password scheme[C]//Proceedings of the working conference on Advanced visual interfaces. 2006: 177-184.Google Scholar
- De Angeli A, Coventry L, Johnson G, Is a picture really worth a thousand words? Exploring the feasibility of graphical authentication systems[J]. International journal of human-computer studies, 2005, 63(1-2): 128-152.Google ScholarDigital Library
- Wiedenbeck S, Waters J, Birget J C, PassPoints: Design and longitudinal evaluation of a graphical password system[J]. International journal of human-computer studies, 2005, 63(1-2): 102-127.Google ScholarDigital Library
- Alzubaidi A, Kalita J. Authentication of smartphone users using behavioral biometrics[J]. IEEE Communications Surveys & Tutorials, 2016, 18(3): 1998-2026.Google ScholarDigital Library
- Shepard K, Wing B, Miles C, Iris Recognition-National Science and Technology Council (NSTC)–Committee on Technology–Committee on Homeland and National Security–Subcommittee on Biometrics (EUA), last updated 31 march 2006[J]. 2006.Google Scholar
- Banerjee S P, Woodard D L. Biometric authentication and identification using keystroke dynamics: A survey[J]. Journal of Pattern Recognition Research, 2012, 7(1): 116-139.Google ScholarCross Ref
- Benegui C, Ionescu R T. Convolutional Neural Networks for User Identification based on Motion Sensors Represented as Images[J]. IEEE Access, 2020, 8: 61255-61266.Google ScholarCross Ref
- Li Y, Hu H, Zhu Z, SCANet: sensor-based continuous authentication with two-stream convolutional neural networks[J]. ACM Transactions on Sensor Networks (TOSN), 2020, 16(3): 1-27.Google Scholar
- Neverova N, Wolf C, Lacey G, Learning human identity from motion patterns[J]. IEEE Access, 2016, 4: 1810-1820.Google ScholarCross Ref
- Papamichail M D, Chatzidimitriou K C, Karanikiotis T, BrainRun: a behavioral biometrics dataset towards continuous implicit authentication[J]. Data, 2019, 4(2): 60.Google ScholarCross Ref
- Stockinger T. Implicit authentication on mobile devices[C]//The Media Informatics Advanced Seminar on Ubiquitous Computing. 2011: 8.Google Scholar
- Frank M, Biedert R, Ma E, Touchalytics: On the applicability of touchscreen input as a behavioral biometric for continuous authentication[J]. IEEE transactions on information forensics and security, 2012, 8(1): 136-148.Google Scholar
- Li L, Zhao X, Xue G. Unobservable re-authentication for smartphones[C]//NDSS. 2013, 56: 57-59.Google Scholar
- Zhang H, Patel V M, Fathy M, Touch gesture-based active user authentication using dictionaries[C]//2015 IEEE Winter Conference on Applications of Computer Vision. IEEE, 2015: 207-214.Google Scholar
- Feng T, Liu Z, Kwon K A, Continuous mobile authentication using touchscreen gestures[C]//2012 IEEE Conference on Technologies for Homeland Security (HST). IEEE, 2012: 451-456.Google Scholar
- Sherman M, Clark G, Yang Y, User-generated free-form gestures for authentication: Security and memorability[C]//Proceedings of the 12th annual international conference on Mobile systems, applications, and services. 2014: 176-189.Google Scholar
- Zhao X, Feng T, Shi W, Mobile user authentication using statistical touch dynamics images[J]. IEEE Transactions on Information Forensics and Security, 2014, 9(11): 1780-1789.Google ScholarDigital Library
- Feng T, Yang J, Yan Z, Tips: Context-aware implicit user identification using touch screen in uncontrolled environments[C]//Proceedings of the 15th Workshop on Mobile Computing Systems and Applications. 2014: 1-6.Google Scholar
- via touch biometrics: An experimental study on smartphones[C]//10th Symposium On Usable Privacy and Security ({SOUPS} 2014). 2014: 187-198.Google Scholar
- Shahzad M, Liu A X, Samuel A. Behavior based human authentication on touch screen devices using gestures and signatures[J]. IEEE Transactions on Mobile Computing, 2016, 16(10): 2726-2741.Google ScholarDigital Library
- Bo C, Zhang L, Jung T, Continuous user identification via touch and movement behavioral biometrics[C]//2014 IEEE 33rd International Performance Computing and Communications Conference (IPCCC). IEEE, 2014: 1-8.Google Scholar
- H Benegui C, Ionescu R T. Adversarial Attacks on Deep Learning Systems for User Identification based on Motion Sensors[C]//International Conference on Neural Information Processing. Springer, Cham, 2020: 752-761.Google Scholar
- Benegui C, Ionescu R T. Convolutional Neural Networks for User Identification based on Motion Sensors Represented as Images[J]. IEEE Access, 2020, 8: 61255-61266.Google ScholarCross Ref
- Ma X, Guo J, Tang S, DCANet: Learning Connected Attentions for Convolutional Neural Networks[J]. arXiv preprint arXiv:2007.05099, 2020.Google Scholar
- Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141.Google Scholar
- Schroff F, Kalenichenko D, Philbin J. Facenet: A unified embedding for face recognition and clustering[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 815-823.Google Scholar
- Deng J, Guo J, Xue N, Arcface: Additive angular margin loss for deep face recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2019: 4690-4699.Google Scholar
- Lin T Y, Goyal P, Girshick R, Focal loss for dense object detection[C]//Proceedings of the IEEE international conference on computer vision. 2017: 2980-2988.Google Scholar
Recommendations
Identity-Based Threshold Proxy Signature from Bilinear Pairings
Delegation of rights is a common practice in the real world. We present two identity-based threshold proxy signature schemes, which allow an original signer to delegate her signing capability to a group of n proxy signers, and it requires a consensus of ...
Simultaneous authentication and secrecy in identity-based data upload to cloud
Most existing works to secure cloud devote to remote integrity check, search and computing on encrypted data. In this paper, we deal with simultaneous authentication and secrecy when data are uploaded to cloud. Observing that cloud is most interesting ...
A non-interactive deniable authentication scheme based on designated verifier proofs
A deniable authentication protocol enables a receiver to identify the source of the given messages but unable to prove to a third party the identity of the sender. In recent years, several non-interactive deniable authentication schemes have been ...
Comments