Quantitative Study on the Impact of Wi-Fi Sensing on User Privacy in Smart Environments
Keywords:
Activity recognition, Channel state information (CSI), Human behaviour recognition, Location identification, Privacy leakage, Smart environments, User privacy, Wi-Fi sensingAbstract
Wi-Fi sensing is an innovative technology that harnesses existing Wi-Fi infrastructure to detect human presence, activities, and physiological signals without additional hardware such as cameras or wearables. By analyzing subtle variations in Channel State Information (CSI), which captures changes in Wi-Fi signal amplitude and phase caused by environmental interactions, sophisticated algorithms can infer movements, locations, and vital signs with remarkable accuracy. This technology offers numerous advantages, including cost-effectiveness, unobtrusive operation, and enhanced privacy compared to traditional sensing methods. However, extensive CSI data collection also raises significant privacy concerns, as unauthorized parties may exploit it to infer sensitive information like identity, behavior, and location. This study investigates these privacy risks and evaluates advanced mitigation techniques, including transmitter-side signal perturbation and receiver-side adversarial learning using autoencoder neural networks. Experimental results demonstrate that these methods effectively reduce privacy leakage without compromising essential sensing functions such as activity recognition. Furthermore, leveraging powerful hardware like the NVIDIA GeForce RTX 3050 enables real-time processing capabilities, supporting practical deployment in smart environments. This work underscores the critical need to integrate privacy protections into Wi-Fi sensing applications to ensure ethical and responsible use across healthcare, security, smart homes, and beyond.
References
Y. He, Y. Chen, Y. Hu and B. Zeng, “WiFi Vision: Sensing, recognition, and detection with commodity MIMO-OFDM WiFi,” in IEEE Internet of Things Journal, vol. 7, no. 9, pp. 8296–8317, Sept. 2020, doi: https://doi.org/10.1109/JIOT.2020.2989426
J. Yang et al., “SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing,” Patterns, vol. 4, no. 3, Mar. 2023, doi: https://doi.org/10.1016/j.patter.2023.100703
D. Varga, “Mitigating data leakage in Wi-Fi CSI benchmarks for human action recognition,” Sensors, vol. 24, no. 24, Dec. 2024, doi: https://doi.org/10.3390/s24248201
G. Senthilkumar, R. Naveenkumar, S. Rajeshkannan, and S. R. Sree, “Efficient energy management in wireless sensor networks based on optimized explicit feature interaction-aware graph neural network,” Peer-to-Peer Networking and Applications, vol. 18, Mar. 2025, doi: https://doi.org/10.1007/s12083-025-01927-8
R. Kolikipogu, S. Shivaputra, R. Naveenkumar, et al., “Improving food safety by IoT-based climate monitoring and control systems for food processing plants,” Remote Sensing in Earth Systems Sciences, vol. 8, pp. 387–399, Jan. 2025, doi: https://doi.org/10.1007/s41976-024-00190-4
S. M. Padmaja et al., “Deep learning in remote sensing for climate-induced disaster resilience: A comprehensive interdisciplinary approach,” Remote Sensing in Earth Systems Sciences, vol. 8, pp. 145–160, Dec. 2024, doi: https://doi.org/10.1007/s41976-024-00178-0
R. N. kumar, M. A. Kumar, “Enhanced fuzzy K-NN approach for handling missing values in medical data mining,” Indian Journal of Science and Technology, vol. 9 no. S1, pp. 1–7, 2016, Available: http://dx.doi.org/10.17485/ijst/2016/v9iS1/94094
S. Bhadra, A. Goon, R. Naveenkumar, S. Roy, T., J. Aich, “Fortifying the resilience and integrity of cyber-physical systems through meticulous assessment,” Nanotechnology Perceptions, vol. 20, no. S16 pp. 1193–1201, Dec. 2024, Available: https://www.researchgate.net/publication/
_Fortifying_the_Resilience_and_Integrity_of_Cyber-Physical_Systems_through_
Meticulous_Assessment
P. Duan, X. Diao, Y. Cao, D. Zhang, B. Zhang, and J. Kong, “A comprehensive survey on Wi-Fi sensing for human identity recognition,” Electronics, vol. 12, no. 23, p. 4858, Jan. 2023, doi: https://doi.org/10.3390/electronics12234858
T. Chen, J. Jiao, and D. Yu, “Strongly coupled phononic crystals resonator with high energy density for acoustic enhancement and directional sensing,” Journal of Sound and Vibration, vol. 529, p. 116911, Jul. 2022, doi: https://doi.org/10.1016/j.jsv.2022.116911
J. Chung, I. Pretzer-Aboff, P. Parsons, K. Falls, and E. Bulut, “Using a device-free Wi-Fi sensing system to assess daily activities and mobility in low-income older adults: Protocol for a feasibility study,” JMIR Research Protocols, vol. 13, Nov. 2024, doi: https://doi.org/10.2196/53447
Y. Shi , X. Zhang , L. Fu, and H. Zhang, “An investigation of the private-attribute leakage in WiFi sensing,” High-Confidence Computing, vol. 4, no. 4, Dec. 2024, doi: https://doi.org/10.1016/j.hcc.2024.100209
N. Kalavani, R. Naveenkumar, S. Bhattacharjee, R. Sarkar, N. Kumar, “Evaluating the performance of machine learning models in cancer prediction through ROC and PRC metrics,” Nanotechnology Perceptions, vol. 20, no. S16, pp. 553–567, 2024, Available: https://www.semanticscholar.org/paper/Evaluating-the-Performance-of-Machine-Learning-in-Kalavani-Naveenkumar/c6d3d997dfb36a6c419697c52c1b8bfff8c848f9
G. Vani, R. Naveenkumar, R. Singha, R. Sarkar, N. Kumar, “Advancing predictive data analytics in IoT and AI leveraging real-time data for proactive operations and system resilience,” Nanotechnology Perceptions, vol. 20, no. S16, pp. 568–582, 2024, doi: https://doi.org/10.62441/nano-ntp.vi.3968
