Evaluating the Influence of Targets and Hand Postures on Touch-based Behavioural Biometrics
summary
Study uses 150,000 touches from 24 users across two sessions a week apart, four target types at 400 screen locations, and trains regression surface models on session one to identify users from session two. Results show small, compactly shaped targets near edges yield the most descriptive patterns, thumb touches are more individual than index touches, full-width targets fail, and a GUI-simulation framework predicts which interfaces will support reliable touch-based ID.
AI-written summary · about
chapters (6)
- 0:00Introduction to touch biometrics
- 2:54Study design and approach
- 7:51Key results and findings
- 10:44Implications for GUI design
- 13:58Building touch biometric systems
- 15:24Q&A session
related talks
06mTouchID: User Authentication on Mobile Devices via Inertial-Touch Gesture Analysis
23mExploring Intentional Behaviour Modifications for Password Typing on Mobile Touchscreen
06mListen to Your Fingers: User Authentication based on Geometry Biometrics of Touch Gesture
25mContinuous Biometrics
20mBiometric Touch Sensing: Seamlessly Augmenting Each Touch with Continuous Authentication
05mFine-Grained and Context-Aware Behavioral Biometrics for Pattern Lock on Smartphones
07mNot Quite Yourself Today: Behaviour-Based Continuous Authentication in IoT Environments
18mZensei: Embedded, Multi-electrode Bioimpedance Sensing for Implicit, Ubiquitous User Recognition