Abstract
Context-based copresence detection schemes are a necessary prerequisite to building secure and usable authentication systems in the Internet of Things (IoT). Such schemes allow one device to verify proximity of another device without user assistance utilizing their physical context (e.g., audio). The state-of-the-art copresence detection schemes suffer from two major limitations: (1) They cannot accurately detect copresence in low-entropy context (e.g., empty room with few events occurring) and insufficiently separated environments (e.g., adjacent rooms), (2) They require devices to have common sensors (e.g., microphones) to capture context, making them impractical on devices with heterogeneous sensors. We address these limitations, proposing Next2You, a novel copresence detection scheme utilizing channel state information (CSI). In particular, we leverage magnitude and phase values from a range of subcarriers specifying a Wi-Fi channel to capture a robust wireless context created when devices communicate. We implement Next2You on off-the-shelf smartphones relying only on ubiquitous Wi-Fi chipsets and evaluate it based on over 95 hours of CSI measurements that we collect in five real-world scenarios. Next2You achieves error rates below 4%, maintaining accurate copresence detection both in low-entropy context and insufficiently separated environments. We also demonstrate the capability of Next2You to work reliably in real-time and its robustness to various attacks.
- [1] . 2016. RSSI-based distributed self-localization for wireless sensor networks used in precision agriculture. IEEE Transactions on Wireless Communications 15, 10 (2016), 6638–6650. Google ScholarDigital Library
- [2] . 2018. Deep neural networks meet CSI-based authentication. arXiv:1812.04715. Retrieved from https://arxiv.org/abs/1812.04715.Google Scholar
- [3] . 2015. Room-level proximity detection using beacon frame from multiple access points. In Proceedings of the 2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. IEEE, 941–945.Google Scholar
- [4] . 2016. Room-level proximity detection based on RSS of dual-band Wi-Fi signals. In Proceedings of the IEEE International Conference on Communications. IEEE, 1–6.Google Scholar
- [5] . 2020. Tech Nation: Number of Internet-Connected Devices Grows to 10 per Home. Retrieved 29 September, 2021 from https://www.aviva.com/newsroom/news-releases/2020/01/tech-nation-number-of-internet-connected-devices-grows-to-10-per-home/.Google Scholar
- [6] . 2010. How to explain individual classification decisions. The Journal of Machine Learning Research 11, 61 (2010), 1803–1831. Google ScholarDigital Library
- [7] . 2020. How to Control the Stability of Training Neural Networks with the Batch Size. Retrieved from https://machinelearningmastery.com/how-to-control-the-speed-and-stability-of-training-neural-networks-with-gradient-descent-batch-size/.Google Scholar
- [8] . 2019. Inside job: Diagnosing bluetooth lower layers using off-the-shelf devices. In Proceedings of the 12th Conference on Security and Privacy in Wireless and Mobile Networks. 186–191. Google ScholarDigital Library
- [9] . 2019. Context-based co-presence detection techniques: A survey. Computers & Security 88 (2019), 101652.Google Scholar
- [10] . 2014. Where are you from? Confusing location distinction using virtual multipath camouflage. In Proceedings of the 20th Annual International Conference on Mobile Computing and Networking. 225–236. Google ScholarDigital Library
- [11] . 2016. Virtual multipath attack and defense for location distinction in wireless networks. IEEE Transactions on Mobile Computing 16, 2 (2016), 566–580. Google ScholarDigital Library
- [12] . 2011. Received-signal-strength-based indoor positioning using compressive sensing. IEEE Transactions on Mobile Computing 11, 12 (2011), 1983–1993. Google ScholarDigital Library
- [13] . 2021. Index of Supplementary Files from “Next2You: Robust Copresence Detection Based on Channel State Information”. ACM Transactions on Internet of Things 1, 1 (2021), 1–30.
DOI: https://doi.org/10.5281/zenodo.5105815Google Scholar - [14] . 2018. Survey and systematization of secure device pairing. IEEE Communications Surveys & Tutorials 20, 1 (2018), 517–550.Google ScholarCross Ref
- [15] . 2019. Perils of zero-interaction security in the Internet of Things. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 3, 1 (2019), 10. Google ScholarDigital Library
- [16] . 2018. The lottery ticket hypothesis: Finding sparse, trainable neural networks. In 7th International Conference on Learning Representations (ICLR’19).Google Scholar
- [17] . 2019. Futurae Authentication Suite. Retrieved 29 September, 2021 from https://www.futurae.com/product/strongauth/.Google Scholar
- [18] . 2020. Punched cards over the air: Cross-technology communication between LTE-U/LAA and WiFi. In Proceedings of the 21st IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks. IEEE.Google Scholar
- [19] . 2016. An adaptive wireless passive human detection via fine-grained physical layer information. Ad Hoc Networks 100, 38 (2016), 38–50. Google ScholarDigital Library
- [20] . 2016. Deep Learning. MIT press. Google ScholarDigital Library
- [21] . 2019. Free your CSI: A channel state information extraction platform for modern Wi-Fi chipsets. In Proceedings of the 13th International Workshop on Wireless Network Testbeds, Experimental Evaluation & Characterization. 21–28. Google ScholarDigital Library
- [22] . 2012. Secure proximity detection for NFC devices based on ambient sensor data. In Proceedings of the European Symposium on Research in Computer Security. Springer, 379–396.Google Scholar
- [23] . 2011. Tool release: Gathering 802.11n traces with channel state information. ACM SIGCOMM CCR 41, 1 (2011), 53. Google ScholarDigital Library
- [24] . 2018. Do you feel what I hear? Enabling autonomous IoT device pairing using different sensor types. In Proceedings of the IEEE Symposium on Security and Privacy. IEEE, 836–852.Google Scholar
- [25] . 2017. Signal detection effects on deep neural networks utilizing raw IQ for modulation classification. In Proceedings of the IEEE Military Communications Conference. IEEE, 121–127.Google Scholar
- [26] . 1989. Multilayer feedforward networks are universal approximators. Neural Networks 2, 5 (1989), 359–366. Google ScholarDigital Library
- [27] . 2014. Feasibility and limits of Wi-Fi imaging. In Proceedings of the 12th ACM Conference on Embedded Network Sensor Systems. 266–279. Google ScholarDigital Library
- [28] . 2015. Sound-proof: Usable two-factor authentication based on ambient sound. In Proceedings of the 24th \(\lbrace\)USENIX\(\rbrace\) Security Symposium (\(\lbrace\)USENIX\(\rbrace\) Security 15). 483–498. Google ScholarDigital Library
- [29] . 2020. Keras: The Python Deep Learning Library. Retrieved 29 September, 2021 from https://keras.io/.Google Scholar
- [30] . 2014. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations (ICLR’15).Google Scholar
- [31] . 2019. Unmasking Clever Hans predictors and assessing what machines really learn. Nature Communications 10, 1 (2019), 1–8.Google ScholarCross Ref
- [32] . 1989. Backpropagation applied to handwritten zip code recognition. Neural Computation 1, 4 (1989), 541–551. Google ScholarDigital Library
- [33] . 2017. A research on CSI-based human motion detection in complex scenarios. In Proceedings of the IEEE 19th International Conference on e-Health Networking, Applications and Services. IEEE, 1–6.Google Scholar
- [34] . 2017. The expressive power of neural networks: A view from the width. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 6232–6240. Google ScholarDigital Library
- [35] . 2019. WiFi sensing with channel state information: A survey. ACM Computing Surveys 52, 3 (2019), 1–36. Google ScholarDigital Library
- [36] . 2019. Internalblue-bluetooth binary patching and experimentation framework. In Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services. 79–90. Google ScholarDigital Library
- [37] . 2014. Zebra: Zero-effort bilateral recurring authentication. In Proceedings of the IEEE Symposium on Security and Privacy. IEEE, 705–720. Google ScholarDigital Library
- [38] . 2014. Smartphones as practical and secure location verification tokens for payments. In Proceedings of the 21st Network and Distributed System Security Symposium. Vol. 14, 23–26.Google Scholar
- [39] . 2017. Neural network application for emitter identification. In Proceedings of the 18th International Radar Symposium. IEEE, 1–8.Google Scholar
- [40] . 2018. Convolutional neural networks for position estimation in TDoA-based locating systems. In Proceedings of the International Conference on Indoor Positioning and Indoor Navigation. IEEE, 1–8.Google Scholar
- [41] . 2018. Over-the-air deep learning based radio signal classification. IEEE Journal of Selected Topics in Signal Processing 12, 1 (2018), 168–179.Google ScholarCross Ref
- [42] . 2019. Probabilistic time of arrival localization. IEEE Signal Processing Letters 26, 11 (2019), 1683–1687.Google Scholar
- [43] . 2020. Acoustic integrity codes: Secure device pairing using short-range acoustic communication. In Proceedings of the 13th ACM Conference on Security and Privacy in Wireless and Mobile Networks. 31–41.Google Scholar
- [44] . 2014. PADS: Passive detection of moving targets with dynamic speed using PHY layer information. In Proceedings of the 20th IEEE International Conference on Parallel and Distributed Systems. IEEE, 1–8.Google Scholar
- [45] . 2017. Right for the right reasons: Training differentiable models by constraining their explanations. In Proceedings of the 26th International Joint Conference on Artificial Intelligence. 2662–2670. Google ScholarDigital Library
- [46] . 2013. 802.11 ad–WLAN at 60 GHz–A Technology Introduction. Rohde & Schwarz.Google Scholar
- [47] . 2018. Shadow Wi-Fi: Teaching smartphones to transmit raw signals and to extract channel state information to implement practical covert channels over Wi-Fi. In Proceedings of the 16th Annual International Conference on Mobile Systems, Applications, and Services. ACM, 256–268. Google ScholarDigital Library
- [48] . 2017. Nexmon: The C-based Firmware Patching Framework. Retrieved 29 September, 2021 from https://nexmon.org.Google Scholar
- [49] . 2012. You are facing the Mona Lisa: Spot localization using PHY layer information. In Proceedings of the 10th International Conference on Mobile Systems, Applications, and Services. 183–196. Google ScholarDigital Library
- [50] . 2017. The applicability of ambient sensors as proximity evidence for NFC transactions. In Proceedings of the IEEE Security and Privacy Workshops. IEEE, 179–188.Google Scholar
- [51] . 2017. Smart user authentication through actuation of daily activities leveraging WiFi-enabled IoT. In Proceedings of the 18th ACM International Symposium on Mobile Ad Hoc Networking and Computing. 1–10. Google ScholarDigital Library
- [52] . 2019. Deep learning for RF signal classification in unknown and dynamic spectrum environments. In Proceedings of the IEEE International Symposium on Dynamic Spectrum Access Networks. IEEE, 1–10.Google Scholar
- [53] . 2019. ZEMFA: Zero-effort multi-factor authentication based on multi-modal gait biometrics. In Proceedings of the 17th International Conference on Privacy, Security and Trust. IEEE, 1–10.Google Scholar
- [54] . 2014. Drone to the rescue: Relay-resilient authentication using ambient multi-sensing. In Proceedings of the International Conference on Financial Cryptography and Data Security. Springer, 349–364.Google Scholar
- [55] . 2018. Sensor-based proximity detection in the face of active adversaries. IEEE Transactions on Mobile Computing 18, 2 (2018), 444–457. Google ScholarDigital Library
- [56] . 2016. The sounds of the phones: Dangers of zero-effort second factor login based on ambient audio. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. ACM, 908–919. Google ScholarDigital Library
- [57] . 2019. Looking Under the Hood of the Connected Car. Retrieved 29 September, 2021 from https://www.techradar.com/news/looking-under-the-hood-of-the-connected-car.Google Scholar
- [58] . 2017. Neural network with unbounded activation functions is universal approximator. Applied and Computational Harmonic Analysis 43, 2 (2017), 233–268.Google ScholarCross Ref
- [59] . 2014. Dropout: A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research 15, 1 (2014), 1929–1958. Google ScholarDigital Library
- [60] . 2018. One billion Apples’ secret sauce: Recipe for the Apple Wireless Direct Link Ad hoc protocol. In Proceedings of the 24th Annual International Conference on Mobile Computing and Networking. ACM, 529–543. Google ScholarDigital Library
- [61] . 2019. A billion open interfaces for eve and mallory: MitM, DoS, and tracking attacks on iOS and macOS through Apple Wireless Direct Link. In Proceedings of the 28th USENIX Conference on Security Symposium. 37–54. Google ScholarDigital Library
- [62] . 2018. A survey on deep transfer learning. In Proceedings of the International Conference on Artificial Neural Networks. Springer, 270–279.Google ScholarCross Ref
- [63] . 2020. Deploy Machine Learning Models on Mobile and IoT Devices. Retrieved 29 September, 2021 from https://www.tensorflow.org/lite.Google Scholar
- [64] . 2020. The Top 50 Fastest Computers in the Weaver Research Group. Retrieved 29 September, 2021 from http://web.eece.maine.edu/ vweaver/group/machines.html.Google Scholar
- [65] . 2014. Comparing and fusing different sensor modalities for relay attack resistance in zero-interaction authentication. In Proceedings of the IEEE International Conference on Pervasive Computing and Communications. IEEE, 163–171.Google Scholar
- [66] . 2019. DoubleEcho: Mitigating context-manipulation attacks in copresence verification. In Proceedings of the IEEE International Conference on Pervasive Computing and Communications. IEEE.Google Scholar
- [67] . 2019. 6 Most Commonly Used IoT Communication Protocols. Retrieved 29 September, 2021 from http://techgenix.com/iot-communication-protocols/.Google Scholar
- [68] . 2017. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 5998–6008. Google ScholarDigital Library
- [69] . 2016. CSI phase fingerprinting for indoor localization with a deep learning approach. IEEE Internet of Things Journal 3, 6 (2016), 1113–1123.Google ScholarCross Ref
- [70] . 2017. BiLoc: Bi-modal deep learning for indoor localization with commodity 5GHz WiFi. IEEE Access 5 (2017), 4209–4220.Google ScholarCross Ref
- [71] . 2017. WiTraffic: Low-cost and non-intrusive traffic monitoring system using WiFi. In Proceedings of the 26th International Conference on Computer Communication and Networks. IEEE, 1–9.Google Scholar
- [72] . 2012. CSI-based indoor localization. IEEE Transactions on Parallel and Distributed Systems 24, 7 (2012), 1300–1309. Google ScholarDigital Library
- [73] . 2020. Auto-Key: Using autoencoder to speed up gait-based key generation in body area networks. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 1 (2020), 1–23. Google ScholarDigital Library
- [74] . 2016. Instant and robust authentication and key agreement among mobile devices. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security. ACM, 616–627. Google ScholarDigital Library
- [75] . 2016. A survey on wireless indoor localization from the device perspective. ACM Computing Surveys 49, 2 (2016), 1–31. Google ScholarDigital Library
- [76] . 2015. Precise power delay profiling with commodity WiFi. In Proceedings of the 21st Annual International Conference on Mobile Computing and Networking. ACM, 53–64. Google ScholarDigital Library
- [77] . 2013. Arraytrack: A fine-grained indoor location system. In Proceedings of the 10th \(\lbrace\)USENIX\(\rbrace\) Symposium on Networked Systems Design and Implementation. 71–84. Google ScholarDigital Library
- [78] . 2013. Securearray: Improving WiFi security with fine-grained physical-layer information. In Proceedings of the 19th Annual International Conference on Mobile Computing & Networking. 441–452. Google ScholarDigital Library
- [79] . 2015. Empirical evaluation of rectified activations in convolutional network. arXiv:1505.00853. Retrieved from https://arxiv.org/abs/1505.00853.Google Scholar
- [80] . 2018. Transceiver design of optimum wirelessly powered full-duplex MIMO IoT devices. IEEE Transactions on Communications 66, 5 (2018), 1955–1969.Google ScholarCross Ref
- [81] . 2013. From RSSI to CSI: Indoor localization via channel response. ACM Computing Surveys 46, 2 (2013), 1–32. Google ScholarDigital Library
- [82] . 2018. Feature Engineering for Machine Learning: Principles and Techniques for Data Scientists. O’Reilly Media, Inc. Google ScholarDigital Library
- [83] . 2020. Et tu Alexa? When commodity WiFi devices turn into adversarial motion sensors. In Proceedings of the 27th Annual Network and Distributed System Security Symposium. The Internet Society.Google Scholar
Index Terms
- Next2You: Robust Copresence Detection Based on Channel State Information
Recommendations
Exact Error Rate Analysis of MIMO-MRC System under Cochannel Interference and Imperfect Channel State Information
In this paper, we derive closed-form solution for the bit error rate of multi-input multi-output (MIMO) system with maximum ratio combining. We consider binary PSK modulation suffers from cochannel interference (CCI) and imperfect channel state ...
Using Channel State Information for Tamper Detection in the Internet of Things
ACSAC '15: Proceedings of the 31st Annual Computer Security Applications ConferenceThe Internet of Things (IoT) is increasingly used for critical applications and securing the IoT has become a major concern. Among other issues it is important to ensure that tampering with IoT devices is detected. Many IoT devices use WiFi for ...
Quadrature spatial modulation based multiuser MIMO transmission system
This study presents a multiuser (MU) multiple‐input multiple‐output (MIMO) downlink transmission scheme based on the quadrature spatial modulation (QSM) concept, which uses the indices of the non‐zero entries in its transmission vector to modulate and ...
Comments