Spoofing Attack Detection in Face Recognition System Using Vision Transformer with Patch-wise Data Augmentation

Kota Watanabe, Koichi Ito, Takafumi Aoki

研究成果: 書籍の章/レポート/Proceedings会議への寄与査読

3 被引用数 (Scopus)

抄録

Spoofing attacks are a serious threat to face recognition systems by malicious third parties since face images can be easily collected from the Internet. In this paper, we propose a spoofing attack detection method using Vision Transformer (ViT), which extracts features based on patches to extract fine features in a face image. We also propose a patch-wise data augmentation to improve the detection accuracy of spoofing attacks. We demonstrate the effectiveness of the proposed method through accuracy evaluation experiments using public datasets.

本文言語英語
ホスト出版物のタイトルProceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1561-1565
ページ数5
ISBN(電子版)9786165904773
DOI
出版ステータス出版済み - 2022
イベント2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022 - Chiang Mai, タイ
継続期間: 2022 11月 72022 11月 10

出版物シリーズ

名前Proceedings of 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022

会議

会議2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2022
国/地域タイ
CityChiang Mai
Period22/11/722/11/10

フィンガープリント

「Spoofing Attack Detection in Face Recognition System Using Vision Transformer with Patch-wise Data Augmentation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル