AI researchers claim 93% accuracy in detecting keystrokes over Zoom audio
ID: 22164290-cece-5f64-aee4-f0cbb6e58d74
STIX ID: report--22164290-cece-5f64-aee4-f0cbb6e58d74
Feed Name: Ars Technica Security
Threat Score
Researchers demonstrated a practical acoustic side-channel attack that records keyboard sounds (via phone or Zoom) and uses deep learning (including self-attention layers) to classify individual keypresses with over 93% accuracy, highlighting a privacy and security vulnerability in laptop keyboards and VoIP scenarios; the work is a proof-of-concept rather than evidence of active exploitation.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.
