EUVIMEDEUVIMED entdecken
Crossref

MuKI-Fi: Multi-Person Keystroke Inference With BFI-Enabled Wi-Fi Sensing

Hongbo Wang, Jingyang Hu, Tianyue Zheng, Jingzhi Hu, Zhe Chen, Hongbo Jiang, Yuanjin Zheng, Jun Luo

IEEE Transactions on Mobile Computing · 2024-10 · 23 (10) · 9835-9850

DOI: 10.1109/tmc.2024.3368339 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-10. Verfasst von Hongbo Wang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 71 Literaturangaben. Gefördert von: National Research Foundation Singapore, Info-communications Media Development Authority, MoE Tier 1.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The contact-free sensing nature of Wi-Fi has been leveraged to achieve privacy breaches such as keystroke inference (KI). However, the use of channel state information (CSI) in existing attacks is highly questionable due to its signal instability and hardness to acquire. Moreover, such Wi-Fi-based attacks are confined to only one victim because Wi-Fi sensing offers insufficient range resolution to physically differentiate multiple victims. To this end, we propose MuKI-Fi to enable, for the first time, multi-person KI, leveraging beamforming feedback information (BFI), a new feature offered by latest Wi-Fi hardware, transmitted in clear-text by smartphones. BFI's characteristics, clear-text communication and signal stability, make it readily acquirable and usable by any other Wi-Fi devices switching to monitor mode without the need for low-level hacking on hardware. Moreover, to improve upon existing KI methods offering very limited generalizability across diversified application scenarios, MuKI-Fi innovates in an adversarial learning scheme to enable its inference generalizable towards unseen scenarios. Finally, we discover that, as a smartphone is in close proximity to a victim, the variations of BFI caused by that victim's keystrokes in such near-field substantially outweigh those caused by other distant victims; this phenomenon naturally allows for multi-person KI. Our extensive evaluations clearly demonstrate that MuKI-Fi can effectively eavesdrop on the keystrokes of multiple subjects, achieving 87.1% accuracy for individual keystrokes and up to 81% top-100 accuracy for stealing passwords from mobile applications (e.g., WeChat) on average.

Förderung

  • National Research Foundation Singapore
  • Info-communications Media Development Authority
  • MoE Tier 1

Zitieren

APA

Wang, H., Hu, J., Zheng, T., Hu, J., Chen, Z., Jiang, H., Zheng, Y., & Luo, J. (2024). MuKI-Fi: Multi-Person Keystroke Inference With BFI-Enabled Wi-Fi Sensing. IEEE Transactions on Mobile Computing, 23(10), 9835-9850. https://doi.org/10.1109/tmc.2024.3368339

Vancouver

Wang H, Hu J, Zheng T, Hu J, Chen Z, Jiang H, et al. MuKI-Fi: Multi-Person Keystroke Inference With BFI-Enabled Wi-Fi Sensing. IEEE Transactions on Mobile Computing. 2024;23(10):9835-9850. doi:10.1109/tmc.2024.3368339

BibTeX
@article{Wang2024,
  author = {Wang, Hongbo and Hu, Jingyang and Zheng, Tianyue and Hu, Jingzhi and Chen, Zhe and Jiang, Hongbo and Zheng, Yuanjin and Luo, Jun},
  title = {MuKI-Fi: Multi-Person Keystroke Inference With BFI-Enabled Wi-Fi Sensing},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2024},
  volume = {23},
  number = {10},
  pages = {9835--9850},
  doi = {10.1109/tmc.2024.3368339}
}
Kostenlos starten →