Abstract
The ubiquitous and fine-grained features of WiFi signals make it promising for realizing contactless authentication. Existing methods, though yielding reasonably good performance in certain cases, are suffering from two major drawbacks: sensitivity to environmental dynamics and over-dependence on certain activities. Thus, the challenge of solving such issues is how to validate human identities under different environments, even with different activities. Toward this goal, in this article, we develop WiTL, a transfer learning–based contactless authentication system, which works by simultaneously detecting unique human features and removing the environment dynamics contained in the signal data under different environments. To correctly detect human features (i.e., human heights used in this article), we design a Height EStimation (HES) algorithm based on Angle of Arrival (AoA). Furthermore, a transfer learning technology combined with the Residual Network (ResNet) and the adversarial network is devised to extract activity features and learn environmental independent representations. Finally, experiments through multi-activities and under multi-scenes are conducted to validate the performance of WiTL. Compared with the state-of-the-art contactless authentication systems, WiTL achieves a great accuracy over 93% and 97% in multi-scenes and multi-activities identity recognition, respectively.
- [1] . 2017. Recognizing keystrokes using WiFi devices. IEEE Journal on Selected Areas in Communications 35, 5 (2017), 1175–1190.Google ScholarDigital Library
- [2] . 2020. CapLoc: Capacitive sensing floor for device-free localization and fall detection. IEEE Access 8 (2020), 187353–187364.Google ScholarCross Ref
- [3] . 2017. Semi-supervised sparse representation based classification for face recognition with insufficient labeled samples. IEEE Transactions on Image Processing 26, 5 (2017), 2545–2560.Google ScholarDigital Library
- [4] . 2020. Device-free near-field human sensing using WiFi signals. Personal and Ubiquitous Computing (2020), 1–14.Google Scholar
- [5] . 2016. Deep residual learning for image recognition. In IEEE CVPR. 770–778.Google Scholar
- [6] . 2016. Deep residual learning for image recognition. In IEEE CVPR. 770–778.Google Scholar
- [7] . 2016. WFID: Passive device-free human identification using WiFi signal. In ACM MOBIQUITOUS. 47–56.Google Scholar
- [8] . 2018. Towards environment independent device free human activity recognition. In ACM MOBICOM. 289–304.Google Scholar
- [9] . 2020. Continuous authentication through finger gesture interaction for smart homes using WiFi. IEEE Transactions on Mobile Computing 20, 11 (2020), 3148–3162.Google Scholar
- [10] . 2015. SpotFi: Decimeter level localization using WiFi. In ACM SIGCOMM. 269–282.Google Scholar
- [11] . 2016. Dynamic-MUSIC: Accurate device-free indoor localization. In ACM UBICOMP. 196–207.Google Scholar
- [12] . 2018. WiAU: An accurate device-free authentication system with ResNet. In IEEE SECON. 109–117.Google Scholar
- [13] . 2020. WiWrite: An accurate device-free handwriting recognition system with COTS WiFi. In IEEE ICDCS. 700–709.Google Scholar
- [14] . 2020. UltraGesture: Fine-grained gesture sensing and recognition. IEEE Transactions on Mobile Computing (2020), to appear.Google Scholar
- [15] . 2018. Authenticating users through fine-grained channel information. IEEE Transactions on Mobile Computing 17, 2 (2018), 251–264.Google ScholarDigital Library
- [16] . 2019. Biometric-Based Physical and Cybersecurity Systems. Springer.Google ScholarCross Ref
- [17] . 2018. Enabling contactless detection of moving humans with dynamic speeds using CSI. ACM Transactions on Embedded Computing Systems 17, 2 (2018), 52:1–52:18.Google ScholarDigital Library
- [18] . 2021. Joint iterative optimization-based low-complexity adaptive hybrid beamforming for massive MU-MIMO systems. IEEE Transactions on Communications 69, 3 (2021), 1707–1722.Google ScholarCross Ref
- [19] . 2020. IDIoT: Towards ubiquitous identification of IoT devices through visual and inertial orientation matching during human activity. In IEEE IoTDI. 40–52.Google Scholar
- [20] . 2017. Smart user authentication through actuation of daily activities leveraging WiFi-enabled IoT. In ACM MobiHoc. 5:1–5:10.Google Scholar
- [21] . 2019. Easy transfer learning by exploiting intra-domain structures. In IEEE ICME. 1210–1215.Google Scholar
- [22] . 2020. Cross-scenario device-free activity recognition based on deep adversarial networks. IEEE Transactions on Vehicular Technology 69, 5 (2020), 5416–5245.Google ScholarCross Ref
- [23] . 2016. Gait recognition using wifi signals. In ACM UBICOMP. 363–373.Google Scholar
- [24] . 2015. Understanding and modeling of wifi signal based human activity recognition. In ACM MOBICOM. 65–76.Google Scholar
- [25] . 2017. PhaseBeat: Exploiting CSI phase data for vital sign monitoring with commodity WiFi devices. In IEEE ICDCS. 1230–1239.Google Scholar
- [26] . 2019. mD-Track: Leveraging multi-dimensionality for passive indoor Wi-Fi tracking. In ACM MOBICOM. 1–16.Google Scholar
- [27] . 2016. FreeSense: Indoor human identification with Wi-Fi signals. In IEEE Globecom. 1–7.Google Scholar
- [28] . 2013. ArrayTrack: A fine-grained indoor location system. In USENIX NSDI. 71–84.Google Scholar
- [29] . 2020. RF-Ear: Contactless multi-device vibration sensing and identification using COTS RFID. In IEEE INFOCOM. 297–306.Google Scholar
- [30] . 2021. An improved KNN-based efficient log anomaly detection method with automatically labeled samples. In ACM TKDD, Vol. 15. 1–22.Google Scholar
- [31] . 2016. WiWho: WiFi-based person identification in smart spaces. In ACM IPSN. 1–12.Google Scholar
- [32] . 2019. FarSense: Pushing the range limit of WiFi-based respiration sensing with CSI ratio of two antennas. In ACM UBICOMP. 1–26.Google Scholar
- [33] . 2020. Exploiting channel gain and phase noise for PHY-layer authentication in massive MIMO systems. IEEE Transactions on Information Forensics and Security 16 (2020), 4265–4279.Google ScholarCross Ref
- [34] . 2020. Physical layer authentication jointly utilizing channel and phase noise in MIMO systems. IEEE Transactions on Communications 68, 4 (2020), 2446–2458.Google ScholarCross Ref
- [35] . 2020. Secure beamforming for full-duplex MIMO two-way untrusted relay systems. IEEE Transactions on Information Forensics and Security 15 (2020), 3775–3790.Google ScholarDigital Library
- [36] . 2017. Perceiving accurate CSI phases with commodity WiFi devices. In IEEE INFOCOM. 72–79.Google Scholar
Index Terms
- A Contactless Authentication System Based on WiFi CSI
Recommendations
WiFi-based human activity recognition through wall using deep learning
AbstractWireless sensing is a promising method that integrates wireless mechanisms with strong sensing capabilities. The current focus of using WiFi Channel State Information (CSI) for human activity recognition (HAR) is the line-of-sight (LoS) path, ...
Wifi-based robust indoor localization for daily activity monitoring
MWSSH '22: Proceedings of the 1st ACM Workshop on Mobile and Wireless Sensing for Smart HealthcareAchieving indoor localization enables several intelligent home applications, such as monitoring overall activities of daily living (ADL) and triggering location-specific IoT devices. In addition, ADL information further facilitates physical and mental ...
WiFi CSI-Based Long-Range Through-Wall Human Activity Recognition with the ESP32
Computer Vision SystemsAbstractWiFi Channel State Information (CSI)-based human activity recognition (HAR) is an unobtrusive method for contactless, long-range sensing in spatially constrained environments while preserving visual privacy. Despite the presence of numerous WiFi-...
Comments