Domain-Agnostic Document Authentication Against Practical Recapturing Attacks

Recapturing attack can be employed as a simple but effective anti-forensic tool for digital document images. Inspired by the document inspection process that compares a questioned document against some known samples, we proposed a document recapture detection scheme by employing a Siamese network to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on information forensics and security 2022, Vol.17, p.2890-2905
Hauptverfasser: Chen, Changsheng, Zhang, Shuzheng, Lan, Fengbo, Huang, Jiwu
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recapturing attack can be employed as a simple but effective anti-forensic tool for digital document images. Inspired by the document inspection process that compares a questioned document against some known samples, we proposed a document recapture detection scheme by employing a Siamese network to compare and extract distinct features in a recaptured document image. The proposed algorithm takes advantage of both metric learning and image forensic techniques, and forms triplets by considering some important factors in document authentication, e.g., document types, resolutions, and content in each image patch. After training with our triplet selection strategy, the resulting feature embedding clusters the genuine samples near the reference while pushing the recaptured samples apart. In the experiment, we consider practical settings under domain differences, such as the variations in printing/imaging devices, substrates, recapturing channels, and document types. To evaluate the robustness of different approaches, we benchmark some popular off-the-shelf machine learning-based approaches, a state-of-the-art document image detection scheme, and the proposed schemes with different network backbones under various experimental protocols. Experimental results show that the proposed scheme consistently outperforms the state-of-the-art approaches under different experimental settings. Specifically, under the most challenging scenario in our experiment, i.e., evaluation across different types of documents (produced by different manufacturers, devices, and substrates), we have achieved 6.92% APCER (Attack Presentation Classification Error Rate) and 8.51% BPCER (Bona Fide Presentation Classification Error Rate) by the proposed network with ResNeXt101 backbone at 5.00% BPCER decision threshold.
ISSN:1556-6013
1556-6021
DOI:10.1109/TIFS.2022.3197054