RadSee: See Your Handwriting Through Walls Using FMCW Radar
Shichen Zhang
Network and Distributed System Security (NDSS) Symposium 2025 · Day 3 · Side Channels 2
In an era where digital interactions dominate, the seemingly anachronistic act of writing by hand might appear to be a bastion of privacy. However, the NDSS Symposium talk "RadSee: See Your Handwriting Through Walls Using FMCW Radar" by Shichen Zhang from Michigan State University shatters this perception, unveiling a groundbreaking system capable of discerning handwritten content from behind physical barriers. This research introduces RadSee, a sophisticated, custom-designed 6 GHz **Frequency-Modulated Continuous Wave (FMCW)** radar system paired with a tailored deep neural network, demonstrating the chilling feasibility of remote, through-wall surveillance of even subtle hand movements.
AI review
Genuine, reproducible attack research with a clearly novel contribution: through-wall handwriting recovery via custom 6 GHz FMCW radar plus a bi-directional LSTM pipeline, hitting ~75% letter accuracy at a $500 hardware cost. The threat model is realistic and the engineering tradeoffs (frequency selection, patch antenna gain, phase-based feature extraction) are well-reasoned. Not a 5 because 75% accuracy still leaves practical gaps for real adversarial deployment, the demo was empirical rather than live, and the defensive section reads like filler.