New (Deep Learning-Enhanced) Acoustic Attack Steals Data from Keystrokes With 95% Accuracy

Long-time Slashdot reader SonicSpike quotes this article from BleepingComputer:A team of researchers from British universities has trained a deep learning model that can steal data from keyboard keystrokes recorded using a microphone with an accuracy of 95%... Such an attack severely affects the target's data security, as it could leak people's passwords, discussions, messages, or other sensitive information to malicious third parties. Moreover, contrary to other side-channel attacks that require special conditions and are subject to data rate and distance limitations, acoustic attacks have become much simpler due to the abundance of microphone-bearing devices that can achieve high-quality audio captures. This, combined with the rapid advancements in machine learning, makes sound-based side-channel attacks feasible and a lot more dangerous than previously anticipated. The researchers achieved 95% accuracy from the smartphone recordings, 93% from Zoom recordings, and 91.7% from Skype. The article suggests potential defenses against the attack might include white noise, "software-based keystroke audio filters," switching to password managers - and using biometric authentication.

Read more of this story at Slashdot.