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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Amada, Takuma, Kakizaki, Kazuya, Miyagawa, Taiki, Ebihara, Akinori F., Shiohara, Kaede, Yamasaki, Toshihiko
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913966126530560
author Amada, Takuma
Kakizaki, Kazuya
Miyagawa, Taiki
Ebihara, Akinori F.
Shiohara, Kaede
Yamasaki, Toshihiko
author_facet Amada, Takuma
Kakizaki, Kazuya
Miyagawa, Taiki
Ebihara, Akinori F.
Shiohara, Kaede
Yamasaki, Toshihiko
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22601
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Deepfake Detection for Electronic Know Your Customer Systems Using Registered Images
Amada, Takuma
Kakizaki, Kazuya
Miyagawa, Taiki
Ebihara, Akinori F.
Shiohara, Kaede
Yamasaki, Toshihiko
Computer Vision and Pattern Recognition
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.
title Robust Deepfake Detection for Electronic Know Your Customer Systems Using Registered Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.22601