Privacy-preserving sensing refers to approaches in WiFi CSI-based human sensing that aim to infer target activities, gestures, or identities while minimizing the exposure or leakage of sensitive personal information beyond what is necessary for the task. It matters for the field because CSI signals passively captured from commodity hardware like ESP32 devices can inadvertently encode identifying biometric characteristics, raising ethical and regulatory concerns that must be addressed before real-world deployment. Key variants include anonymization techniques that suppress identity-linked features in the CSI representation, federated or on-device learning strategies that avoid transmitting raw signals to centralized servers, and adversarial training methods that explicitly disentangle sensitive attributes from task-relevant features within deep learning pipelines such as those benchmarked in frameworks like SenseFi.
Source Papers
- A Tutorial on Privacy, RCM and Its Implications in WLAN ↗ — A Tutorial on Privacy, RCM and Its Implications in WLAN
- CSI-Based NTC Using Ambient WiFi: Channel Selection, Topology Control and Traffic Interference ↗ — CSI-Based NTC Using Ambient WiFi: Channel Selection, Topolog
- CSI-Chain: A Complete End-to-End Framework for WiFi CSI Sensing ↗ — CSI-Chain: A Complete End-to-End Framework for WiFi CSI Sens
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- Device-Free Passive Identity Identification via WiFi Signals ↗ — Device-Free Passive Identity Identification via WiFi Signals
- Efficient machine learning for Wi-Fi CSI-based human activity recognition using fast Monte Carlo based feature extraction ↗ — Efficient machine learning for Wi-Fi CSI-based human activit
- SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing ↗ — SenseFi: A library and benchmark on deep-learning-empowered