No abstract

No abstract

No abstract

Touch-based verification-the use of touch gestures (e.g., swiping, zooming, etc.) to authenticate users of touch screen devices-has recently been widely evaluated for its potential to serve as a second layer of defense to the PIN lock mechanism. In all performance evaluations of touch-based authentication systems however, researchers have assumed naïve (zero-effort) forgeries in which the attacker makes no effort to mimic a given gesture pattern.In this paper we demonstrate that a simple "Lego" robot driven by input gleaned from general population swiping statistics can generate forgeries that achieve alarmingly high penetration rates against touch-based authentication systems. Using the best classification algorithms in touch-based authentication, we rigorously explore the effect of the attack, finding that it increases the Equal Error Rates of the classifiers by between 339% and 1004% depending on parameters such as the failure-to-enroll threshold and the type of touch stroke generated by the robot. The paper calls into question the zero-effort impostor testing approach used to benchmark the performance of touch-based authentication systems.

No abstract