Researchers at Cornell University have uncovered a groundbreaking AI-driven attack that can steal passwords with jaw-dropping accuracy. By analysing the sounds of keystrokes, an AI model was trained to identify each key's unique sound.
When tested on a MacBook Pro, it achieved an astounding 95% accuracy in identifying pressed keys. But it doesn't stop there - in a Zoom call experiment, the AI reproduced keystrokes with 93% accuracy, and 91.7% accuracy over Skype.
Shockingly, the volume of typing doesn't matter - the AI focuses on waveform, intensity, and timing. As if this wasn't alarming enough, the attack can be carried out using simple off-the-shelf equipment. With just a smartphone and a nearby microphone, a malicious actor could effortlessly steal your passwords and sensitive information. Stay vigilant!
- CyberBeat
CyberBeat is a grassroots initiative from a team of producers and subject matter experts, driven out of frustration at the lack of media coverage, responding to an urgent need to provide a clear, concise, informative and educational approach to the growing fields of Cybersecurity and Digital Privacy.
If you have a story of interest, a comment, a concern or if you'd just like to say Hi, please contact us
We couldn't do this without the support of our sponsors and contributors.