In a recent study conducted by UK-based computer scientists, it has been discovered that hackers can potentially use artificial intelligence tools to steal user passwords with astonishing accuracy. By “listening” to the sounds produced by keystrokes on a MacBook Pro, an AI model was trained to replicate typed passwords with an impressive 95% precision. Even during a Zoom video conference, the AI tool was able to accurately reproduce keystrokes with a record-breaking 93% precision through the laptop’s microphone.
This alarming discovery highlights the potential risk of cyberattacks known as “acoustic side channel attacks.” Many individuals are unaware that their typing can be monitored by malicious actors, leading to breaches of their online accounts. The researchers emphasize that keyboard acoustic emanations are not only readily accessible as an attack vector but also often disregarded by victims, who may hide their screens while neglecting to obfuscate their keyboard’s sound.
To assess accuracy, researchers pressed 36 keys on the laptop 25 times each, varying the pressure and finger used for each press. The AI model was successful in reproducing these keystrokes with an impressive 95% accuracy rate. By “listening” to distinct elements of each key press, such as sound wavelengths, the program was able to identify and replicate the keystrokes effectively.
The study was conducted by Joshua Harrison of Durham University, Ehsan Toreini of the University of Surrey, and Maryam Mehrnezhad at Royal Holloway University of London. It sheds light on the potential dangers of AI tools in the hands of hackers. Furthermore, it highlights the lack of awareness among the general public regarding the risks associated with such cyberattacks.
This discovery adds to a growing list of concerns raised by renowned experts in the field, including Sam Altman, founder of OpenAI, and billionaire Elon Musk. Without proper safeguards and regulations, AI poses a significant threat to humanity. The need for robust security measures to counteract potential abuses of AI technology has never been more crucial.
Denial of responsibility! VigourTimes is an automatic aggregator of Global media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, and all materials to their authors. For any complaint, please reach us at – [email protected]. We will take necessary action within 24 hours.
