PulseAugur
LIVE 14:49:04
research · [1 source] ·
0
research

Selfie motion analysis detects deepfakes in mobile identity verification

Researchers have developed a new method called CanSelfie that uses motion data captured during selfie-taking to help detect deepfakes and injection attacks in mobile identity verification. By analyzing accelerometer data, which preserves gravity and orientation cues, the system can distinguish between genuine user movements and those indicative of spoofing attempts. This approach aims to provide an additional layer of security beyond traditional camera-based detection, addressing new European regulatory requirements. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enhances mobile identity verification security by using passive motion analysis to combat deepfakes and injection attacks.

RANK_REASON Academic paper detailing a new method for detecting deepfakes using sensor data.

Read on arXiv cs.LG →

COVERAGE [1]

  1. arXiv cs.LG TIER_1 · Erkka Rantahalvari, Olli Silv\'en, Zinelabidine Boulkenafet, Constantino \'Alvarez Casado ·

    Selfie-Capture Dynamics as an Auxiliary Signal Against Deepfakes and Injection Attacks for Mobile Identity Verification

    arXiv:2605.00218v1 Announce Type: cross Abstract: Mobile remote identity verification (RIdV) systems are exposed to attacks that manipulate or replace the facial video stream, including presentation attacks, real-time deepfakes, and video injection. Recent European requirements, …