Robust Deepfake Detection for Electronic Know Your Customer Systems Using Registered Images

TL;DR

This paper introduces a robust deepfake detection method tailored for eKYC systems, leveraging registered images and temporal inconsistencies to identify face swapping and reenactment even under degraded image conditions.

Contribution

The proposed approach combines temporal analysis with registered image comparison, enhancing deepfake detection accuracy and robustness specifically for eKYC applications.

Findings

Accurately detects face swapping and reenactment.

Robust against various unseen image degradations.

Improves detection performance with larger training datasets.

Abstract

In this paper, we present a deepfake detection algorithm specifically designed for electronic Know Your Customer (eKYC) systems. To ensure the reliability of eKYC systems against deepfake attacks, it is essential to develop a robust deepfake detector capable of identifying both face swapping and face reenactment, while also being robust to image degradation. We address these challenges through three key contributions: (1)~Our approach evaluates the video's authenticity by detecting temporal inconsistencies in identity vectors extracted by face recognition models, leading to comprehensive detection of both face swapping and face reenactment. (2)~In addition to processing video input, the algorithm utilizes a registered image (assumed to be genuine) to calculate identity discrepancies between the input video and the registered image, significantly improving detection accuracy. (3)~We find that employing a face feature extractor trained on a larger dataset enhances both detection performance and robustness against image degradation. Our experimental results show that our proposed method accurately detects both face swapping and face reenactment comprehensively and is robust against various forms of unseen image degradation. Our source code is publicly available https://github.com/TaikiMiyagawa/DeepfakeDetection4eKYC.