Exploring Intentional Behaviour Modifications for Password Typing on Mobile Touchscreen
summary
Prestudy (N=114) yields visual key-shape annotations that 80%+ of participants correctly interpret; lab study (N=24) runs 37 tasks across two sessions one week apart and shows users can intentionally alter flight time, hold time, touch area, touch-to-key offset but certain combinations trip errors. Co-located modifications are easier, increasing number and distribution raise mistakes and slow typing. A Gaussian-mixture ID model loses accuracy under modification but retains signal, and a random-forest detector distinguishes modifications with high accuracy, suggesting usable entropy gains.
AI-written summary · about
chapters (12)
- 0:00Start
- 0:56Motivation
- 2:52Roadmap
- 3:27Keystroke Feature Selection
- 4:39Pre-study
- 5:34Proposed text annotations
- 6:28Study design
- 8:02Procedure
- 9:15Results
- 14:41User Feedback
- 15:53Extending password space
- 16:56Take away
related talks
19mEvaluating the Influence of Targets and Hand Postures on Touch-based Behavioural Biometrics
24mSecurity at your fingertips: Theory → Practice!
05mFine-Grained and Context-Aware Behavioral Biometrics for Pattern Lock on Smartphones
06mTouchID: User Authentication on Mobile Devices via Inertial-Touch Gesture Analysis
19mDesign and Evaluation of a Data-Driven Password Meter
27mFast, Lean, and Accurate: Modeling Password Guessability Using Neural Networks
06mListen to Your Fingers: User Authentication based on Geometry Biometrics of Touch Gesture
25mThermanator and the Thermal Residue Attack