Abstract
Indoor localization is an emerging application domain for the navigation and tracking of people and assets. Ubiquitously available Wi-Fi signals have enabled low-cost fingerprinting-based localization solutions. Further, the rapid growth in mobile hardware capability now allows high-accuracy deep learning--based frameworks to be executed locally on mobile devices in an energy-efficient manner. However, existing deep learning--based indoor localization solutions are vulnerable to access point (AP) attacks. This article presents an analysis into the vulnerability of a convolutional neural network--based indoor localization solution to AP security compromises. Based on this analysis, we propose a novel methodology to maintain indoor localization accuracy, even in the presence of AP attacks. The proposed secured neural network framework (S-CNNLOC) is validated across a benchmark suite of paths and is found to deliver up to 10× more resiliency to malicious AP attacks compared to its unsecured counterpart.
- The Plane Crash That Gave Americans GPS. 2019. Retrieved from https://www.the atlantic.com/technology/archive/2014/11/the-plane-crash-that-gave-americans-gps/382204/.Google Scholar
- A brief history of GPS. 2019. Retrieved fromhttps://www.pcworld.com/article/2000276/a-brief-history-of-gps.Google Scholar
- This GPS Spoofing Hack Can Really Mess with Your Google Maps Trips. 2019. Retrieved from https://www.forbes.com/sites/thomasbrewster/2018/07/12/google-maps-gps-hack-takes-victims-to-ghost-locations/.Google Scholar
- Spoofing in the Black Sea: What really happened? 2019. Retrieved from https://www.gpsworld.com/spoofing-in-the-black-sea-what-really-happened/.Google Scholar
- Wi-Fi RTT (IEEE 802.11mc). 2019. Retrieved from https://www.source.android.com/devices/tech/connect/wifi-rtt.Google Scholar
- Top 33 indoor localization services in the US. 2019. Retrieved from https://www.technavio.com/blog/top-33-indoor-location-based-services-lbs-companies-in-the-us.Google Scholar
- Y. Chen, W. Sun, and J. Juang. 2010. Outlier detection technique for RSS-based localization problems in wireless sensor networks. In Proceedings of the International Conference on Structural Integrity and Exhibition (SICE’10).Google Scholar
- A. Khalajmehrabadi, N. Gatsis, D. J. Pack, and D. Akopian. 2017. A joint indoor WLAN localization and outlier detection scheme using LAS-SO and elastic-net optimization techniques. IEEE Trans. Mobile Comput. 16, 8 (2017), 2079--2092.Google Scholar
Digital Library
- J. Schmitz, M. Hernández, and R. Mathar. 2016. Real-time in-door localization with TDOA and distributed software de-fined radio: Demonstration abstract. In Proceedings of the Conference on Information Processing in Sensor Networks (IPSN’16).Google Scholar
- D. Vasisht, S. Kumar, and D. Katabi. 2015. Sub-nanosecond time of flight on commercial Wi-Fi cards. In Proceedings of the Special Interest Group on Data Communication Conference (SIGCOMM’15).Google Scholar
- Z. Chen, Z. Li, X. Zhang, G. Zhu, Y. Xu, J. Xiong, and X. Wang. 2017. AWL: Turning spatial aliasing from foe to friend for accurate WiFi localization. In Proceedings of the Conference on Emerging Networking Experiments and Technologies (CoNEXT’17).Google Scholar
- Z. Lu, W. Wang, and C. Wang. 2014. Modeling, evaluation and detection of jamming attacks in time-critical wireless applications. IEEE Trans. Mobile Comput. 13, 8 (2014), 1746--1759.Google Scholar
Cross Ref
- E. Soltanaghaei, A. Kalyanaraman, and K. Whitehouse. 2018. Multipath tri-angulation: Decimeter-level wi-fi localization and orientation with a single unaided receiver. In Proceedings of the Conference on Mobile Systems, Applications, and Services (MobiSys’18).Google Scholar
- S. Pasricha, V. Ugave, C. W. Anderson, and Q. Han. 2015. LearnLoc: A framework for smart indoor localization with embedded mobile devices. In Proceedings of the Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS’15).Google Scholar
- A. Mittal, S. Tiku, and S. Pasricha. 2018. Adapting convolutional neural networks for indoor localization with smart mobile devices. In Proceedings of the Conference on the Great Lakes Symposium on VLSI (GLSVLSI’18).Google Scholar
- W. Meng, W. Xiao, W. Ni, and L. Xie. 2011. Secure and robust Wi-Fi finger-printing indoor localization. In Proceedings of the Conference on Indoor Positioning and Indoor Navigation (IPIN’11).Google Scholar
- W. Zhang et al. 2016. Deep neural networks for wireless localization in indoor and outdoor environments. Neurocomputing 194 (2016), 279--287.Google Scholar
Digital Library
- Y. K. Cheng, H. J. Chou, and R. Y. Chang. 2016. Machine-learning indoor localization with access point selection and signal strength reconstruction. In Proceedings of the Vehicular Technology Conference (VTC’16).Google Scholar
- P. Bahl and V. Padmanabhan. 2000. RADAR: An in-building RF-based user location and tracking system. In Proceedings of the IEEE International Conference on Computer Communications (INFOCOM’00).Google Scholar
- Ubisense Research Network. 2017. Retrieved from http://www.ubisense.net/.Google Scholar
- P. Dickinson, G. Cielniak, O. Szymanezyk, and M. Mannion. 2016. Indoor positioning of shoppers using a network of Bluetooth Low Energy beacons. In Proceedings of the Indoor Positioning and Indoor Navigation (IPIN’16).Google Scholar
- S. Lau, T. Lin, T. Huang, I. Ng, and P. Huang. 2009. A measurement study of zigbee-based indoor localization systems under RF interference. In Proceedings of the Workshop on Experimental Evaluation and Characterization (WIN-TECH’09).Google Scholar
- H. Zou et al. 2016. A robust indoor positioning system based on the procrustes analysis and weighted extreme learning machine. IEEE Trans. Wireless Comput. 15, 2 (2016), 1252--1266.Google Scholar
Digital Library
- L. Chang, X. Chen, J. Wang, D. Fang, C. Liu, Z. Tang, and W. Nie. 2015. TaLc: Time adaptive indoor localization with little cost. In Proceedings of the MobiCom Workshop on Challenged Networks (CHANTS’15).Google Scholar
- D. Barbará, R. Goel, and S. Jajodia. 2000. Using checksums to detect data corruption. In Proceedings of the International Conference on Extending Database Technology.Google Scholar
- L. Ou, Z. Qin, Y. Liu, H. Yin, Y. Hu, and H. Chen. 2016. Multi-user location correlation protection with differential privacy. In Proceedings of the International Conference on Parallel and Distributed Systems (ICPADS’16).Google Scholar
- C. Wu, Z. Yang, and Y. Liu. 2015. Smartphones based crowdsourcing for indoor localization. In IEEE Trans. Mobile Comput. 14, 2 (2015), 444--457.Google Scholar
Cross Ref
- L. Lazos and M. Krunz. 2011. Selective jamming/dropping insider attacks in wireless mesh networks. IEEE Trans. Netw. 25, 1 (2011), 30--34.Google Scholar
Digital Library
- Z. Lu, W. Wang, and C. Wang. 2014. Modeling, evaluation and detection of jamming attacks in time-critical wireless applications. IEEE Trans. Mobile Comput. 13, 8 (2014), 1746—1759.Google Scholar
Cross Ref
- W. Xu, W. Trappe, Y. Zhang, and T. Wood. 2005. The feasibility of launch-ing and detecting jamming attacks in wireless networks. In Proceedings of the Conference on Mobile ad hoc Networking and Computing (MobiHoc’05).Google Scholar
- C. Wang, L. Zhu, and L. Gong et al. 2018. Accurate sybil attack detection based on fine-grained physical channel information. Sensors 18, 3 (2018), 878.Google Scholar
Cross Ref
- A. A. A. Silva et al. 2015. Predicting model for identifying the malicious activity of nodes in MANETs. In Proceedings of the Symposium on Computers and Communication (ISCC’15).Google Scholar
- Y. LeCun et al. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86, 11 (1998), 2278--2324.Google Scholar
Cross Ref
- J. S. Lee. 1983. Digital image smoothing and the sigma filter. Comput. Vis. Graph. Image Process. 24, 2 (1983), 255--269.Google Scholar
Cross Ref
- X. Wang et al. 2015. DeepFi: Deep learning for indoor fingerprinting using channel state information. In Proceedings of the Wireless Communications and Networking Conference (WCNC’15).Google Scholar
- J. Machaj, P. Brida, and R. Piché. 2011. Rank based fingerprinting algorithm for indoor positioning. In Proceedings of the Indoor Positioning and Indoor Navigation (IPIN’11).Google Scholar
- Y. Shu et al. 2016. Gradient-based fingerprinting for indoor localization and tracking. IEEE Trans. Indust. Electr. 63, 4 (2016), 2424--2433.Google Scholar
Cross Ref
- F. Zhang, N. Cai, J. Wu, G. Cen, H. Wang, and X. Chen. 2018. Image de-noising method based on a deep convolution neural network. IET Image Process. 12, 4 (2018), 485--493.Google Scholar
Cross Ref
- HTC U11. Retrieved from https://www.htc.com/us/smartphones/htc-u11.Google Scholar
- MAC Address Clone on my TP-Link. Retrieved from https://www.tp-link.com/us/support/faq/68/.Google Scholar
- M. Mohammadi, A. Al-Fuqaha, M. Guizani, and J. Oh. 2018. Semisupervised deep reinforcement learning in support of iot and smart city ser-vices. IoT J. 5, 2 (2018), 624--635.Google Scholar
- J. A. Larcom and H. Liu. 2013. Modeling and characterization of GPS spoof-ing. In Proceedings of the Conference on Technologies for Homeland Security (HST’13).Google Scholar
- C. Bonebrake and L. Ross O'Neil. 2014. Attacks on GPS time reliability. IEEE Secur. Priv. 12, 3 (2014), 82--84.Google Scholar
Cross Ref
- K. Jansen, M. Schäfer, D. Moser, V. Lenders, C. Pöpper, and J. Schmitt. 2018. Crowd-GPS-Sec: Leveraging crowdsourcing to detect and localize GPS spoofing attacks. In Proceedings of the Symposium on Security and Privacy (SP’18).Google Scholar
- K. Corina. and A. MacWilliams. 2011. Overview of indoor positioning technologies for context aware AAL applications. Ambient Assisted Living, 2011.Google Scholar
- V. Spasova and I. Iliev. 2014. A survey on automatic fall detection in the context of ambient assisted living systems. Int. J. Adv. Comput. Res. 4, 1 (2014), 94.Google Scholar
- Á. M. Guerrero-Higueras, N. DeCastro-García, F. J. Rodríguez-Lera, and V. Matellán. 2017. Empirical analysis of cyber-attacks to an indoor real time localization system for autonomous robots. Comput. Secur. 70 (2017), 422--435.Google Scholar
Cross Ref
- Á. M. Guerrero-Higueras, N. Matellan. 2018. Detection of cyber-attacks to indoor real time localization systems for autonomous robots. Robot. Auton. Syst. 99 (2018), 75--83.Google Scholar
Cross Ref
- C. Langlois, S. Tiku, and S. Pasricha. 2017. Indoor localization with smartphones: Harnessing the sensor suite in your pocket. IEEE Cons. Electr. Mag. 6, 4 (2017), 70--80.Google Scholar
Cross Ref
- S. Tiku and S. Pasricha. 2019. PortLoc: A portable data-driven indoor localization framework for smartphones. IEEE Des. Test 36, 5 (2019), 18--26.Google Scholar
Cross Ref
- S. Tiku, S. Pasricha, B. Notaros, and Q. Han. 2019. SHERPA: A lightweight smartphone heterogeneity resilient portable indoor localization framework. In Proceedings of the IEEE International Conference on Embedded Software and Systems (ICESS’19).Google Scholar
Index Terms
Overcoming Security Vulnerabilities in Deep Learning--based Indoor Localization Frameworks on Mobile Devices
Recommendations
Adversarial Attacks on Deep Learning-based Floor Classification and Indoor Localization
WiseML '21: Proceedings of the 3rd ACM Workshop on Wireless Security and Machine LearningWith the great advances in location-based services (LBS), Wi-Fi localization has attracted great interest due to its ubiquitous availability in indoor environments. Deep neural network (DNN) is a powerful method to achieve high localization performance ...
QuickLoc: Adaptive Deep-Learning for Fast Indoor Localization with Mobile Devices
Indoor localization services are a crucial aspect for the realization of smart cyber-physical systems within cities of the future. Such services are poised to reinvent the process of navigation and tracking of people and assets in a variety of indoor and ...
Adapting Convolutional Neural Networks for Indoor Localization with Smart Mobile Devices
GLSVLSI '18: Proceedings of the 2018 on Great Lakes Symposium on VLSIIndoor localization is emerging as an important application domain for enhanced navigation (or tracking) of people and assets in indoor locales such as buildings, malls, and underground mines. Most indoor localization solutions proposed in prior work do ...








Comments