The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
Use Your PIN Securely: Acoustic-Based Second-Factor User Authentication With Enhanced Tap Biometrics
- Published
- Record updated
Summary
Researchers present TapPass, an acoustic second-factor authentication mechanism that derives device-bound, user-specific tap biometrics from hand-reflected ultrasonic signals during PIN entry. A joint deep learning framework combining adversarial and contrastive learning extracts the biometric features, and an incremental learning strategy supports long-term adaptation. In experiments with 50 participants, TapPass reached an average authentication accuracy of 93.24%, outperforming the state-of-the-art work by 14.48%, with a standard deviation of 1.42% over an 8-week longitudinal study.