
The information displayed in the AIM should not be reported as representing the official views of the OECD or of its member countries.
UK researchers developed a deep learning model capable of decoding keystrokes from audio recordings with up to 95% accuracy using nearby smartphones or Zoom calls. This AI-driven acoustic side-channel attack demonstrates a significant privacy and cybersecurity risk, enabling potential theft of sensitive data through common microphone-equipped devices.[AI generated]


























