According to alarming results from a study published earlier this month, hackers could use artificial intelligence tools to steal user passwords with near-perfect accuracy by “listening” to an unsuspecting person’s keystrokes.
A group of British computer scientists trained an artificial intelligence model to identify the sounds made by keystrokes on the 2021 version of a MacBook Pro – dubbed the “popular standard laptop”.
When the AI program was activated on a nearby smartphone, it was able to reproduce the entered password with a whopping 95% accuracy. according to the study results published by Cornell University.
The hacker-friendly AI tool was also extremely accurate when “eavesdropping” on the laptop’s microphone during a Zoom video conference.
Researchers said it reproduced keystrokes with 93% accuracy – a record for the medium.
The researchers warned that many users are unaware of the risk that malicious actors could monitor their inputs to hack accounts – a type of cyberattack they dubbed a “sonic side-channel attack.”
“The ubiquity of acoustic emanations from keyboards not only makes them a readily available attack vector, but also causes victims to underestimate their emanations (and therefore not try to hide them),” the study states.
“For example, when typing a password, people routinely hide their screens, but do little to mask the sound of their keyboards.”
To measure accuracy, the researchers pressed 36 keys on the laptop a total of 25 times, with each press having “different levels of pressure and finger pressure.”
The program was able to “hear” identifying elements of each keystroke, such as the sound wavelengths. The smartphone, an iPhone 13 mini, was placed 17 centimeters from the keyboard.
The research was conducted by Joshua Harrison from Durham University, Ehsan Toreini from the University of Surrey and Maryam Mehrnezhad from Royal Holloway University of London.
The possibility of AI tools helping hackers is just another risk factor for the burgeoning technology.
A number of well-known experts, from OpenAI founder Sam Altman to billionaire Elon Musk and others, have warned that AI could pose a significant threat to humankind without proper safeguards.