Papers
Topics
Authors
Recent
Search
2000 character limit reached

Security Analysis of WiFi-based Sensing Systems: Threats from Perturbation Attacks

Published 24 Apr 2024 in cs.CR | (2404.15587v1)

Abstract: Deep learning technologies are pivotal in enhancing the performance of WiFi-based wireless sensing systems. However, they are inherently vulnerable to adversarial perturbation attacks, and regrettably, there is lacking serious attention to this security issue within the WiFi sensing community. In this paper, we elaborate such an attack, called WiIntruder, distinguishing itself with universality, robustness, and stealthiness, which serves as a catalyst to assess the security of existing WiFi-based sensing systems. This attack encompasses the following salient features: (1) Maximizing transferability by differentiating user-state-specific feature spaces across sensing models, leading to a universally effective perturbation attack applicable to common applications; (2) Addressing perturbation signal distortion caused by device synchronization and wireless propagation when critical parameters are optimized through a heuristic particle swarm-driven perturbation generation algorithm; and (3) Enhancing attack pattern diversity and stealthiness through random switching of perturbation surrogates generated by a generative adversarial network. Extensive experimental results confirm the practical threats of perturbation attacks to common WiFi-based services, including user authentication and respiratory monitoring.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (62)
  1. Y. Ma, G. Zhou, and S. Wang, “WiFi Sensing with Channel State Information: A Survey,” ACM Computing Surveys, vol. 52, no. 3, pp. 1–36, 2019.
  2. H. Kong, L. Lu, J. Yu, and et al, “Push the Limit of WiFi-based User Authentication towards Undefined Gestures,” in IEEE INFOCOM, Virtual, 2022.
  3. Y. Meng, J. Li, H. Zhu, and et al, “Revealing Your Mobile Password via WiFi Signals: Attacks and Countermeasures,” IEEE Transactions on Mobile Computing, vol. 19, no. 2, pp. 432–449, 2020.
  4. R. Xiao, J. Liu, J. Han, and et al, “OneFi: One-Shot Recognition for Unseen Gesture via COTS WiFi,” in ACM SenSys, Coimbra, Portugal, 2021.
  5. C. Li, M. Liu, and Z. Cao, “WiHF: Gesture and User Recognition With WiFi,” IEEE Transactions on Mobile Computing, vol. 21, no. 2, pp. 757–768, 2022.
  6. J. Wang, X. Zhang, Q. Gao, H. Yue, and H. Wang, “Device-free wireless localization and activity recognition: A deep learning approach,” IEEE Transactions on Vehicular Technology, vol. 66, no. 7, pp. 6258–6267, 2016.
  7. J. Wang, Q. Gao, X. Ma, Y. Zhao, and Y. Fang, “Learning to Sense: Deep Learning for Wireless Sensing with Less Training Efforts,” IEEE Wireless Communications, vol. 27, no. 3, pp. 156–162, 2020.
  8. J. Wang, Q. Gao, M. Pan, and Y. Fang, “Device-free wireless sensing: Challenges, opportunities, and applications,” IEEE Network, vol. 32, no. 2, pp. 132–137, 2018.
  9. Y. Zheng, Y. Zhang, K. Qian, and et al, “Zero-Effort Cross-Domain Gesture Recognition with Wi-Fi,” in ACM MobiSys, Seoul, South Korea, 2019.
  10. H. Kong, L. Lu, J. Yu, and et al, “MultiAuth: Enable Multi-User Authentication with Single Commodity WiFi Device,” in ACM MobiHoc, Shanghai, China, 2021, pp. 31–40.
  11. J. Xiong and K. Jamieson, “Arraytrack: A Fine-grained Indoor Location System,” in Lombard, IL, Atlanta, USA & Cambridge, UK, 2013.
  12. W. Jiang, C. Miao, F. Ma, and et al, “Towards Environment Independent Device Free Human Activity Recognition,” in ACM MobiCom, New Delhi, India, 2018.
  13. Z. Li, Y. Wu, J. Liu, and et al, “AdvPulse: Universal, Synchronization-Free, and Targeted Audio Adversarial Attacks via Subsecond Perturbations,” in ACM CCS, Virtual, 2020.
  14. H. Cao, H. Jiang, D. Liu, and J. Xiong, “Evidence in hand: Passive vibration response-based continuous user authentication,” in 2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS), 2021, pp. 1020–1030.
  15. S. Li, A. Neupane, S. Paul, and et al, “Stealthy Adversarial Perturbations Against Real-Time Video Classification Systems,” in NDSS, San Diego, California, 2019.
  16. Y. Nan, X. Wang, L. Xing, X. Liao, and et al, “Are You Spying on Me? Large-Scale Analysis on IoT Data Exposure through Companion Apps,” in USENIX Security Symposium, Anaheim, USA, 2023.
  17. Y. Zhou, H. Chen, C. Huang, and et al, “WiAdv: Practical and Robust Adversarial Attack against WiFi-Based Gesture Recognition System,” ACM UbiComp/IMWUT, 2019.
  18. Z. Liu, C. Xu, E. Sie, and et al, “Exploring Practical Vulnerabilities of Machine Learning-based Wireless Systems,” in USENIX NSDI, Boston, USA, 2023.
  19. J. Liu, Y. He, C. Xiao, and et al, “Physical-World Attack towards WiFi-based Behavior Recognition,” in IEEE INFOCOM, Virtual, 2022.
  20. A. Bahramali, M. Nasr, A. Houmansadr, and et al, “Robust Adversarial Attacks Against DNN-Based Wireless Communication Systems,” in ACM CCS, Virtual, 2022.
  21. B. Kim, Y. E. Sagduyu, K. Davaslioglu, and et al, “Channel-Aware Adversarial Attacks Against Deep Learning-Based Wireless Signal Classifiers,” IEEE Transactions on Wireless Communications, vol. 21, no. 6, pp. 3868–3880, 2022.
  22. B. Flowers, R. M. Buehrer, and W. C. Headley, “Evaluating Adversarial Evasion Attacks in the Context of Wireless Communications,” IEEE Transactions on Information Forensics and Security, vol. 15, no. 1, pp. 1102–1113, 2020.
  23. Y. Xie, R. Jiang, X. Guo, and et al, “Universal Targeted Adversarial Attacks Against mmWave-based Human Activity Recognition,” in IEEE INFOCOM, New York area, USA, 2023.
  24. W. Zhang, S. Zhao, L. Liu, and et al, “Attack on Practical Speaker Verification System Using Universal Adversarial Perturbations,” in IEEE ICASSP, Toronto, Ontario, Canada, 2021.
  25. R. Wang, Z. Huang, Z. Chen, and et al, “Anti-Forgery: Towards a Stealthy and Robust DeepFake Disruption Attack via Adversarial Perceptual-aware Perturbations,” in IJCAI, Messe Wien, Austria, 2022.
  26. S. Xie, H. Wang, Y. Kong, and et al, “Universal 3-dimensional perturbations for black-box attacks on video recognition systems,” in IEEE S&P, San Francisco, CA, 2022.
  27. X. Zhang, X. Zheng, and W. Mao, “Adversarial Perturbation Defense on Deep Neural Networks,” ACM Computing Surveys, vol. 54, no. 8, pp. 1–36, 2021.
  28. Y. Liu, Z. Tan, H. Hu, and et al, “Channel Estimation for OFDM,” IEEE Communications Surveys & Tutorials, vol. 16, no. 4, pp. 1891–1908, 2014.
  29. H. Cao, D. Liu, H. Jiang, R. Wang, Z. Chen, and J. Xiong, “Lipauth: Hand-dependent light intensity patterns for resilient user authentication,” ACM Trans. Sen. Netw., 2023.
  30. C. Han, K. Wu, Y. Wang, and et al., “WiFall: Device-free Fall Detection by Wireless Networks,” Toronto, Canada, 2014.
  31. J. Luo, H. Cao, H. Jiang, Y. Yang, and C. Zhe, “mimocrypt: Multi-user privacy-preserving wi-fi sensing via mimo encryption,” in 2024 IEEE Symposium on Security and Privacy (SP), 2024.
  32. Z. Chen, T. Zheng, C. Hu, and et al, “ISACoT: Integrating Sensing with Data Traffic for Ubiquitous IoT Devices,” IEEE Communications Magazine, vol. 61, no. 5, pp. 98–104, 2023.
  33. Y. Zeng, D. Wu, J. Xiong, and et al, “MultiSense: Enabling Multi-Person Respiration Sensing with Commodity WiFi,” ACM UbiComp/IMWUT, 2020.
  34. B. Huang, R. Yang, B. Jia, and et al, “A Theoretical Analysis on Sampling Size in WiFi Fingerprint-Based Localization,” IEEE TVT, vol. 70, no. 4, 2021.
  35. B. Guo, W. Zuo, S. Wang, and et al, “WePos: Weak-Supervised Indoor Positioning with Unlabeled WiFi for On-Demand Delivery,” ACM UbiComp/IMWUT 2022, 2022.
  36. P. Huang, X. Zhang, S. Yu, and et al, “IS-WARS: Intelligent and Stealthy Adversarial Attack to Wi-Fi-based Human Activity Recognition Systems,” IEEE Transactions on Dependable and Secure Computing, vol. 19, no. 6, pp. 3899–3912, 2021.
  37. S. Cheng, Y. Dong, T. Pang, and et al, “Improving black-box adversarial attacks with a transfer-based prior,” in NeurIPS, Virtual, 2019.
  38. J. Yang, R. Xu, R. Li, and et al, “An adversarial perturbation oriented domain adaptation approach for semantic segmentation,” in AAAI, New York, USA, 2017.
  39. X. Li, Y. Jiang, C. Liu, S. Liu, H. Luo, and S. Yin, “Playing against Deep-Neural-Network-Based Object Detectors: A Novel Bidirectional Adversarial Attack Approach,” IEEE Transactions on Artificial Intelligence, vol. 3, no. 1, pp. 20–28, 2021.
  40. Z. Wei, J. Chen, X. Wei, and et al, “Heuristic Black-box Adversarial Attacks on Video Recognition Models,” in AAAI, New York, USA, 2020.
  41. L. Zhang, Y. Meng, J. Yu, and et al, “Voiceprint Mimicry Attack Towards Speaker Verification System in Smart Home,” in IEEE INFOCOM, Virtual, 2020, pp. 377–386.
  42. L. Cimini, “Analysis and simulation of a digital mobile channel using orthogonal frequency division multiplexing,” IEEE Transactions on Computers, vol. 33, no. 7, pp. 665–675, 1985.
  43. Z. Yang, Y. Zhang, K. Qian, and et al, “SLNet: A Spectrogram Learning Neural Network for Deep Wireless Sensing,” in USENIX NSDI, Boston, USA, 2023.
  44. H. Li, X. Chen, J. Wang, and et al, “DAFI: WiFi-Based Device-Free Indoor Localization via Domain Adaptation,” ACM UbiComp/IMWUT, 2022.
  45. J. Zhao, M. Mathieu, and Y. LeCun, “Energy-based Generative Adversarial Network,” in ICLR, Toulon, France, 2017.
  46. M. Salzmann et al., “Learning transferable adversarial perturbations,” NeurIPS, 2021.
  47. Q. Huang, I. Katsman, H. He, and et al, “Enhancing adversarial example transferability with an intermediate level attack,” in IEEE/CVF ICCV, Seoul, Korea, 2019, pp. 4733–4742.
  48. Z. Wang, H. Guo, Z. Zhang, and et al, “Feature importance-aware transferable adversarial attacks,” in IEEE/CVF ICCV, Virtual, 2020.
  49. S. Nagaraj, S. Khan, C. Schlegel, and et al, “Differential preamble detection in packet-based wireless networks,” IEEE Transactions on Wireless Communications, vol. 8, no. 2, pp. 599–607, 2009.
  50. J. Zhu, Y. Im, S. Mishra, and et al, “Calibrating time-variant, device-specific phase noise for cots wifi devices,” in ACM Sensys, Delft, The Netherlands, 2020.
  51. M. Kotaru, K. Joshi, D. Bharadia, and et al, “Spotfi: Decimeter level localization using wifi,” in ACM SIGCOMM, London, United Kingdom, 2015.
  52. Y. Zeng, J. Liu, J. Xiong, and et al, “Exploring multiple antennas for long-range wifi sensing,” ACM IMWUT/UbiComp, 2021.
  53. J. Choi, “Sensor-Aided Learning for Wi-Fi Positioning With Beacon Channel State Information,” IEEE Transactions on Wireless Communications, vol. 21, no. 7, pp. 5251–5264, 2022.
  54. Wikimedia, “IEEE 802.11,” https://en.wikipedia.org/wiki/IEEE_802.11, 2023, online; accessed 13 Dctober 2023.
  55. R. Eberhart and J. Kennedy, “Particle Swarm Optimization,” in IEEE ICNN, vol. 4, 1995, pp. 1942–1948.
  56. H. Cao, H. Jiang, D. Liu, and et al, “Evidence in Hand: Passive Vibration Response-based Continuous User Authentication,” 2021.
  57. Mango Communications, “WARP v3 Kit,” http://mangocomm.com/products/kits/warp-v3-kit/, 2023, online; accessed 10 October 2023.
  58. NI, “USRP X310,” https://www.ettus.com/all-products/x310-kit/, 2023, online; accessed 10 October 2023.
  59. X. Li, L. Chang, F. Song, and et al, “CrossGR: Accurate and Low-cost Cross-target Gesture Recognition Using Wi-Fi,” ACM UbiComp/IMWUT, 2021.
  60. L. Zheng, S. Bi, S. Wang, and et al, “ResMon: Domain-adaptive Wireless Respiration State Monitoring via Few-shot Bayesian Deep Learning,” IEEE Internet of Things Journal, 2023.
  61. L. Zhang, C. Wang, and D. Zhang, “Wi-PIGR: Path Independent Gait Recognition with Commodity Wi-Fi,” IEEE Transactions on Mobile Computing, vol. 21, no. 9, pp. 3414–3427, 2021.
  62. H. Ding, H. Yue, J. Liu, P. Si, and Y. Fang, “Energy-efficient Secondary Traffic Scheduling with MIMO Beamforming,” in IEEE GLOBECOM, San Diego, USA, 2015.
Citations (2)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up

Tweets

Sign up for free to view the 1 tweet with 0 likes about this paper.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up for Free