Get Started
Home
Topics
Search
Library
Research questionHow can mobile identity verification detect facial-video spoofing when the camera stream is manipulated or replaced?Remote identity checks may receive replayed, synthesized, or injected facial video rather than a genuine camera capture. This makes it difficult to distinguish legitimate users from presentation and stream-manipulation attacks using facial video alone.
AI
Computer Vision
Image & Video Processing
Machine Learning
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.Selfie-Capture Dynamics as an Auxiliary Signal Against Deepfakes and Injection Attacks for Mobile Identity VerificationThe evidence covers selfie-capture motion traces recorded in the CanSelfie dataset from 30 participants, including stationary, handheld, and temporally shifted attack-proxy scenarios. The study evaluates multivariate time-series classifiers and anomaly detectors across sensor configurations and temporal windows, but does not establish performance for cross-device, cross-session, or real injection attacks.research paper · Sep 2, 2026
Related questions
How can ViT-based video facial-expression recognition detect subtle, localized temporal changes that global attention overlooks?How can we generate realistic synthetic identity documents for verification evaluation when real documents are scarce?How can video-based palm-vein authentication remain reliable despite surface, illumination, motion, and temperature variation?How can gaze trajectories be synthesized for biometric authentication while preserving identity, task context, and subjective state?