WiFi signals can recognize your keystrokes: WiKey paper reports 97.5% detection
rickasaurus · x · 2026-11-02
A shared IEEE paper, Recognizing Keystrokes Using WiFi Devices, shows WiFi signals can be exploited to identify keyboard input. Hand and finger movements create unique patterns in channel state information (CSI), enabling keystroke recognition. The WiKey system uses only off-the-shelf hardware — a TP-Link router and a Lenovo laptop — achieving over 97.5% keystroke detection and 96.4% accuracy, with 100+ citations. The poster comments that this side-channel attack is "pretty hopeless" to defend against.
More from Safety
- Researcher warns personal agents may leak sensitive data within months — himanshustwts · 2026-11-02
- NeurIPS paper: deleting harmful data may be what makes AI unsafe — apsarathchandar · 2026-11-02
- Podcast: AI verification hardware could enable a binding US-China AI treaty — wfithian · 2026-11-02
- Critical Langflow Flaws Allow Unauthenticated RCE via MCP; Fix in 1.13.0 — jedisct1 · 2026-11-02
- Yoshua Bengio warns frontier AI labs lack convincing safety plans at Berlin summit — Yoshua_Bengio · 2026-11-02
- Ex-Google CISO Phil Venables: 70% of vulnerability effort is deployment, not discovery — philvenables · 2026-11-02