New user keystroke impersonation attack uses AI to evade detection
Security researchers at the Ben-Gurion University of the Negev (BGU) have developed a new attack technique that uses artificial intelligence (AI) to let compromised USB keyboards generate malicious keystrokes that match legitimate user behavior. Malboard, as the researchers have dubbed the attack, could enable threat actors to avoid detection by security solutions designed to detect malicious keystrokes.
The study mentions that “Malboard was effective in two scenarios: by a remote attacker using wireless communication to communicate, and by an inside attacker or employee who physically operates and uses Malboard.”
In order to avoid attacks like Malboard, the researchers propose new methods for detecting malicious keystrokes. These methods include “(1) the keyboard’s power consumption; (2) the keystrokes’ sound; and (3) the user’s behavior associated with his or her ability to respond to typographical errors.” According to one of the authors of the study, the suggested methods could be used to detect Malboard attacks “with no misses and no false positives.”